WO2022135272A1 - 三维模型重建方法、设备和存储介质 - Google Patents

三维模型重建方法、设备和存储介质 Download PDF

Info

Publication number
WO2022135272A1
WO2022135272A1 PCT/CN2021/138868 CN2021138868W WO2022135272A1 WO 2022135272 A1 WO2022135272 A1 WO 2022135272A1 CN 2021138868 W CN2021138868 W CN 2021138868W WO 2022135272 A1 WO2022135272 A1 WO 2022135272A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
information
dimensional
image acquisition
model reconstruction
Prior art date
Application number
PCT/CN2021/138868
Other languages
English (en)
French (fr)
Inventor
殷佳欣
Original Assignee
花瓣云科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 花瓣云科技有限公司 filed Critical 花瓣云科技有限公司
Priority to US18/258,716 priority Critical patent/US20240046560A1/en
Priority to EP21909268.1A priority patent/EP4250238A4/en
Publication of WO2022135272A1 publication Critical patent/WO2022135272A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/2625—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects for obtaining an image which is composed of images from a temporal image sequence, e.g. for a stroboscopic effect
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/02—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/50—Constructional details
    • H04N23/54—Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/2624—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects for obtaining an image which is composed of whole input images, e.g. splitscreen

Definitions

  • Three-dimensional (3 Dimensional, 3D) model reconstruction refers to the process of establishing a mathematical model suitable for computer identification and processing based on single-view or multi-view images. Engineering, games, shopping, teaching and other scenarios.
  • a 3D model reconstruction method in the related art mainly includes the following steps: step S101, collecting two-dimensional images of the reconstructed object from different angles and different distances through an image acquisition device, during the image acquisition process, the reconstructed object is fixed, and only the image acquisition device is moved; step S102: Perform feature extraction, image matching, feature matching, three-dimensional structure, depth estimation, gridding, adding texture, positioning, etc. on the collected two-dimensional image to obtain a 3D model corresponding to the reconstructed object.
  • step S102 the process of generating the 3D model from the two-dimensional image is very time-consuming. If the reconstructed 3D model fails to meet the user's quality requirements, the 3D model needs to be reconstructed again, which wastes the user's time and causes poor user experience.
  • the present application provides a three-dimensional model reconstruction method, device and storage medium, so as to help solve the problems of waste of user time and poor user experience in the 3D model reconstruction solution in the prior art.
  • an embodiment of the present application provides a three-dimensional model reconstruction method, the method includes: sending three-dimensional model reconstruction index information to a server device, where the three-dimensional model reconstruction index information is used to represent a three-dimensional model reconstruction requirement; receiving the An image acquisition scheme sent by a server device, the image acquisition scheme is used to guide the acquisition of a two-dimensional image of the reconstructed object; according to the image acquisition scheme, a two-dimensional image of the reconstructed object is acquired, and the two-dimensional image is used for three-dimensional Model reconstruction.
  • a reconstruction communication link is added in the 3D model reconstruction process, and the 3D model reconstruction requirements and the image acquisition scheme are communicated, so as to avoid the problem that the 3D model reconstruction fails due to the collected two-dimensional images that do not meet the 3D model reconstruction requirements. Improve the success rate of a reconstruction.
  • the image acquisition scheme includes an image acquisition guidance program; the acquiring a two-dimensional image of the reconstructed object according to the image acquisition scheme includes: according to the guidance of the image acquisition guidance program, acquiring A two-dimensional image of the reconstructed object.
  • the acquisition of the two-dimensional image is guided by the image acquisition guide program, which improves the convenience and accuracy of the two-dimensional image acquisition.
  • collecting the two-dimensional image of the reconstructed object according to the guidance of the image collection guide program includes: outputting moving direction guide information, where the moving direction guide information is used to prompt the target The position is moved; in response to an image acquisition instruction input by the user, a two-dimensional image of the reconstructed object is acquired.
  • the terminal device is guided to move to the target position through the moving direction guidance information, which is convenient for the user to operate and improves the friendliness of the human-computer interaction.
  • the image acquisition guidance program includes an image acquisition sequence
  • the outputting moving direction guidance information includes: according to the image acquisition sequence, after completing the first two-dimensional image acquisition at the first acquisition position Afterwards, outputting moving direction guidance information from the first collection position to the second collection position, where the movement direction guidance information from the first collection position to the second collection position is used to prompt movement to the second collection position.
  • the method further includes: when it is determined that the target position is moved, outputting prompt information for reaching the target position.
  • the terminal device when the terminal device moves to the target position, it outputs the prompt information of reaching the target position, so as to prevent the user from triggering the image acquisition action of the terminal device when not reaching the target position or exceeding the target position, and affecting the quality of the collected two-dimensional images. quality.
  • the acquiring the two-dimensional image of the reconstructed object according to the guidance of the image acquisition guidance program includes: controlling a robotic arm to drive the terminal device to move to a location through the image acquisition guidance program. A target position, and a two-dimensional image of the reconstructed object is acquired.
  • the acquisition of the two-dimensional image by the robotic arm can be controlled more accurately, and the acquisition accuracy of the two-dimensional image is higher.
  • the method further includes: displaying a preview image of the acquired two-dimensional image.
  • displaying the preview image of the two-dimensional image that has been collected can facilitate the user to know the progress of collecting the two-dimensional image in real time.
  • the user can also check according to the preview image to avoid the omission of the two-dimensional image.
  • the method further includes: preprocessing the collected two-dimensional image to obtain summary information of the two-dimensional image; sending the abstract of the two-dimensional image to the server device information, the summary information is used to judge whether the collected two-dimensional image meets the reconstruction requirements of the three-dimensional model; in response to the image supplementary acquisition scheme sent by the server device, according to the image supplementary acquisition scheme, supplementary acquisition of the reconstruction A two-dimensional image of an object; or, receiving a two-dimensional image satisfying condition instruction sent by the server device, where the two-dimensional image satisfying condition instruction is used to indicate that the acquired two-dimensional image can meet the reconstruction requirements of the three-dimensional model.
  • the terminal device and the server device further communicate the quantity and quality of the acquired two-dimensional images, which can further improve the success rate of one-time reconstruction.
  • the image supplementary acquisition scheme includes defect prompt information, and the defect prompt information is used to prompt the cause of the defect.
  • the user can determine the cause of the defect according to the defect prompt information, which facilitates the supplementary acquisition of the two-dimensional image.
  • the sending the three-dimensional model reconstruction index information to the server device includes: in response to the three-dimensional model reconstruction index input information and/or the three-dimensional model reconstruction index selection information input by the user, sending the three-dimensional model to the server device Reconstruction index information, wherein the three-dimensional model reconstruction index information corresponds to the three-dimensional model reconstruction index input information and/or the three-dimensional model reconstruction index selection information.
  • the three-dimensional model reconstruction index is determined according to the index information input by the user, so as to meet the user's personalized demand for the 3D model reconstruction.
  • the three-dimensional model reconstruction index information includes quality index information and/or object index information, where the quality index information is used to represent the quality of the three-dimensional model to be reconstructed, and the object index information is used for Characterize the dimensions of the 3D model that needs to be reconstructed.
  • the quality index information and/or the object index information are used as the three-dimensional model reconstruction index to meet the user's personalized requirements for the quality and/or size of the reconstructed three-dimensional model.
  • the quality index information includes the mean difference MSE and/or the intersection ratio IoU of the 3D model to be reconstructed; and/or the object index information includes the 3D model to be reconstructed. Length, width and height and/or the diameter of the sphere corresponding to the 3D model to be reconstructed.
  • the three-dimensional model reconstruction index information further includes performance index information, where the performance index information is used to represent the resources expected to be consumed by the user during the three-dimensional model reconstruction process.
  • the user communicates with the server device the resources expected to be consumed, such as time resources and/or computing resources, through the performance index information, so that the server device can perform the 3D model reconstruction operation within the range of the resources expected by the user to satisfy the user's expectations of Individual needs that consume resources.
  • the resources expected to be consumed such as time resources and/or computing resources
  • the method further includes: receiving an instruction sent by the server device that the performance index cannot meet the three-dimensional model reconstruction requirement, and the performance index cannot meet the three-dimensional model reconstruction requirement instruction is used to represent user expectations The resources consumed cannot meet the requirements of 3D model reconstruction.
  • the server device determines that the resources expected by the user cannot meet the 3D model reconstruction requirements
  • the information is sent to the terminal device, so that the user can adjust the 3D model reconstruction index information to avoid 3D model reconstruction failure.
  • the method further includes: receiving estimated performance information sent by the server device, where the estimated performance information includes estimated resources to be consumed in the process of reconstructing the three-dimensional model.
  • the server device estimates the resources that need to be consumed in the 3D model reconstruction process, such as time resources and/or computing resources, and sends the estimated resource consumption information to the terminal device, so that the user can judge whether it is possible to Meet the demand for resource consumption.
  • the image acquisition scheme includes text-based image acquisition guidance information and/or audio-video image acquisition guidance information.
  • the guidance of two-dimensional image acquisition is performed through text-based image acquisition guidance information and/or audio-video image acquisition guidance information, which is easy to implement and suitable for relatively simple two-dimensional image acquisition scenarios.
  • an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium includes a stored program, wherein when the program runs, a device where the computer-readable storage medium is located is controlled to execute the first The method of any one of the aspects.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 2 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of a 3D model reconstruction scene provided by an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a three-dimensional model reconstruction method provided by an embodiment of the present application.
  • 5A-5D are schematic diagrams of a three-dimensional model reconstruction index configuration scene according to an embodiment of the present application.
  • 6A-6C are schematic diagrams of an image acquisition scene provided by an embodiment of the present application.
  • FIGS. 7A-7C are schematic diagrams of an image acquisition guidance scene provided by an embodiment of the present application.
  • FIG. 10 is a schematic diagram of a supplementary image acquisition scheme provided by an embodiment of the present application.
  • FIG. 11 is a schematic diagram of another image supplementary acquisition scheme provided by an embodiment of the present application.
  • the reconstruction object involved in the embodiment of the present application is a 3D object that the user prepares for 3D model reconstruction, and the 3D model generated by the 3D model reconstruction is the 3D model corresponding to the reconstruction object.
  • the photos involved in the embodiments of the present application are photos of the reconstructed object, and in some embodiments, the photos may also be described as images, pictures, or the like.
  • the information interaction between hardware devices involved in the embodiments of this application can also be understood as the information interaction between software tools carried on the hardware device.
  • the information interaction between the terminal device and the server device can be understood as the information interaction on the terminal device Information interaction between an integrated development environment (IDE) and the cloud computing environment (AR Cloud) on a server device.
  • the IDE is used to provide the application program of the program development environment, including tools such as code editor, compiler, debugger, and graphical user interface.
  • the IDE is used to upload photos, view the execution progress, preview the 3D model, etc.
  • AR Cloud is a combination of a continuous point cloud map and real world coordinates. It builds a real-time updated 3D digital world model by scanning the real world.
  • AR Cloud is used to perform the 3D model reconstruction calculation process. For example, perform photogrammetry pipeline calculations on images uploaded by the IDE to generate 3D models.
  • the photogrammetry pipeline is a tool that uses captured photos to create 3D models.
  • the electronic device involved in the embodiment of the present application includes a terminal device 101 and a server device 102 , and the terminal device 101 and the server device 102 are interconnected through a wired or wireless communication network for information transmission.
  • the communication network may be a local area network or a wide area network switched by a relay device.
  • the communication network can be a near field communication network such as a wifi hotspot network, a wifi P2P network, a Bluetooth network, a zigbee network, or a near field communication (near field communication, NFC) network.
  • the communication network may be a third-generation mobile communication technology (3rd-generation wireless telephone technology, 3G) network, a fourth-generation mobile communication technology (the 4th generation mobile communication technology, 4G) network ) network, the 5th-generation mobile communication technology (5G) network, the future evolved public land mobile network (PLMN) or the Internet, etc.
  • 3G third-generation mobile communication technology
  • 4G fourth-generation mobile communication technology
  • 5G 5th-generation mobile communication technology
  • PLMN future evolved public land mobile network
  • Internet etc.
  • the terminal device 101 can also be a tablet computer, a personal computer (PC), a personal digital assistant (PDA), a smart watch, a netbook, a wearable electronic device, an augmented reality technology (augmented reality, AR) devices, virtual reality (VR) devices, in-vehicle devices, robots, smart glasses, etc.
  • a tablet computer a personal computer (PC)
  • PDA personal digital assistant
  • smart watch a netbook
  • a wearable electronic device an augmented reality technology (augmented reality, AR) devices, virtual reality (VR) devices, in-vehicle devices, robots, smart glasses, etc.
  • AR augmented reality technology
  • VR virtual reality
  • the user can trigger the terminal device 101 and input some instructions in the terminal device 101 to cause the terminal device 101 to perform corresponding operations, or to enable the terminal device 101 to perform corresponding information interaction with the server device 102 .
  • the embodiment of the present application does not limit the triggering form of the instruction, for example, it may be triggered by devices such as a touch screen, a mouse, a keyboard, and a key.
  • FIG. 2 it is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the electronic device 200 may be either the terminal device 101 in FIG. 1 or the server device 102 in FIG. 1 .
  • the electronic device 200 may include a processor 210, an external memory interface 220, an internal memory 221, a universal serial bus (USB) interface 230, a charge management module 240, a power management module 241, a battery 242, an antenna 1, an antenna 2 , mobile communication module 250, wireless communication module 260, audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, sensor module 280, buttons 290, motor 291, indicator 292, camera 293, display screen 294, and Subscriber identification module (subscriber identification module, SIM) card interface 295 and so on.
  • SIM Subscriber identification module
  • the sensor module 280 may include a pressure sensor 280A, a gyroscope sensor 280B, an air pressure sensor 280C, a magnetic sensor 280D, an acceleration sensor 280E, a distance sensor 280F, a proximity light sensor 280G, a fingerprint sensor 280H, a temperature sensor 280J, a touch sensor 280K, and ambient light.
  • Sensor 280L Bone Conduction Sensor 280M, etc.
  • the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 200 .
  • the electronic device 200 may include more or less components than shown, or combine some components, or separate some components, or arrange different components.
  • the illustrated components may be implemented in hardware, software, or a combination of software and hardware.
  • the processor 210 may include one or more processing units, for example, the processor 210 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.
  • application processor application processor, AP
  • modem processor graphics processor
  • image signal processor image signal processor
  • ISP image signal processor
  • controller video codec
  • digital signal processor digital signal processor
  • baseband processor baseband processor
  • neural-network processing unit neural-network processing unit
  • the controller can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.
  • a memory may also be provided in the processor 210 for storing instructions and data.
  • the memory in processor 210 is cache memory.
  • the memory may hold instructions or data that have just been used or recycled by the processor 210 . If the processor 210 needs to use the instruction or data again, it can be called directly from the memory. Repeated accesses are avoided, and the waiting time of the processor 210 is reduced, thereby improving the efficiency of the system.
  • the processor 210 may include one or more interfaces.
  • the interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous transceiver (universal asynchronous transmitter) receiver/transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and / or universal serial bus (universal serial bus, USB) interface, etc.
  • I2C integrated circuit
  • I2S integrated circuit built-in audio
  • PCM pulse code modulation
  • PCM pulse code modulation
  • UART universal asynchronous transceiver
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB universal serial bus
  • the I2C interface is a bidirectional synchronous serial bus that includes a serial data line (SDA) and a serial clock line (SCL).
  • the processor 210 may contain multiple sets of I2C buses.
  • the processor 210 can be respectively coupled to the touch sensor 280K, the charger, the flash, the camera 293 and the like through different I2C bus interfaces.
  • the processor 210 can couple the touch sensor 280K through the I2C interface, so that the processor 210 communicates with the touch sensor 280K through the I2C bus interface, so as to realize the touch function of the electronic device 200 .
  • the I2S interface can be used for audio communication.
  • the processor 210 may contain multiple sets of I2S buses.
  • the processor 210 may be coupled with the audio module 270 through an I2S bus to implement communication between the processor 210 and the audio module 270 .
  • the audio module 270 can transmit audio signals to the wireless communication module 260 through the I2S interface, so as to realize the function of answering calls through the Bluetooth headset.
  • the PCM interface can also be used for audio communications, sampling, quantizing and encoding analog signals.
  • the audio module 270 and the wireless communication module 260 may be coupled through a PCM bus interface.
  • the audio module 270 can also transmit audio signals to the wireless communication module 260 through the PCM interface, so as to realize the function of answering calls through a Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.
  • the UART interface is a universal serial data bus used for asynchronous communication.
  • the bus may be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication.
  • a UART interface is typically used to connect the processor 210 with the wireless communication module 260 .
  • the processor 210 communicates with the Bluetooth module in the wireless communication module 260 through the UART interface to implement the Bluetooth function.
  • the audio module 270 can transmit audio signals to the wireless communication module 260 through the UART interface, so as to realize the function of playing music through the Bluetooth headset.
  • the GPIO interface can be configured by software.
  • the GPIO interface can be configured as a control signal or as a data signal.
  • the GPIO interface may be used to connect the processor 210 with the camera 293, the display screen 294, the wireless communication module 260, the audio module 270, the sensor module 280, and the like.
  • the GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.
  • the USB interface 230 is an interface that conforms to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like.
  • the USB interface 230 can be used to connect a charger to charge the electronic device 200, and can also be used to transmit data between the electronic device 200 and peripheral devices. It can also be used to connect headphones to play audio through the headphones.
  • the interface can also be used to connect other electronic devices, such as AR devices.
  • the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration, and does not constitute a structural limitation of the electronic device 200 .
  • the electronic device 200 may also adopt different interface connection manners in the foregoing embodiments, or a combination of multiple interface connection manners.
  • the charging management module 240 is used to receive charging input from the charger.
  • the charger may be a wireless charger or a wired charger.
  • the charging management module 240 may receive charging input from the wired charger through the USB interface 230 .
  • the charging management module 240 may receive wireless charging input through the wireless charging coil of the electronic device 200 . While the charging management module 240 charges the battery 242 , the power management module 241 can also supply power to the electronic device.
  • the power management module 241 is used to connect the battery 242 , the charging management module 240 and the processor 210 .
  • the power management module 241 receives input from the battery 242 and/or the charging management module 240, and supplies power to the processor 210, the internal memory 221, the display screen 294, the camera 293, and the wireless communication module 260.
  • the power management module 241 can also be used to monitor parameters such as battery capacity, battery cycle times, battery health status (leakage, impedance).
  • the power management module 241 may also be provided in the processor 210 .
  • the power management module 241 and the charging management module 240 may also be provided in the same device.
  • the wireless communication function of the electronic device 200 may be implemented by the antenna 1, the antenna 2, the mobile communication module 250, the wireless communication module 260, the modulation and demodulation processor, the baseband processor, and the like.
  • Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals.
  • Each antenna in electronic device 200 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.
  • the antenna 1 can be multiplexed as a diversity antenna of the wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.
  • the mobile communication module 250 may provide a wireless communication solution including 2G/3G/4G/5G, etc. applied on the electronic device 200 .
  • the mobile communication module 250 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), and the like.
  • the mobile communication module 250 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation.
  • the mobile communication module 250 can also amplify the signal modulated by the modulation and demodulation processor, and then convert it into electromagnetic waves for radiation through the antenna 1 .
  • at least part of the functional modules of the mobile communication module 250 may be provided in the processor 210 .
  • at least part of the functional modules of the mobile communication module 250 may be provided in the same device as at least part of the modules of the processor 210 .
  • the modem processor may include a modulator and a demodulator.
  • the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal.
  • the demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing.
  • the low frequency baseband signal is processed by the baseband processor and passed to the application processor.
  • the application processor outputs sound signals through audio devices (not limited to the speaker 270A, the receiver 270B, etc.), or displays images or videos through the display screen 294 .
  • the modem processor may be a stand-alone device.
  • the modem processor may be independent of the processor 210, and may be provided in the same device as the mobile communication module 250 or other functional modules.
  • the wireless communication module 260 can provide applications on the electronic device 200 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellites Wireless communication solutions such as global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared technology (IR).
  • WLAN wireless local area networks
  • BT Bluetooth
  • GNSS global navigation satellite system
  • FM frequency modulation
  • NFC near field communication
  • IR infrared technology
  • the wireless communication module 260 may be one or more devices integrating at least one communication processing module.
  • the wireless communication module 260 receives electromagnetic waves via the antenna 2 , modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 210 .
  • the wireless communication module 260 can also receive the signal to be sent from the processor 210 , perform frequency modulation on the signal, amplify the signal, and then convert it into an electromagnetic wave for radiation through the antenna 2 .
  • the antenna 1 of the electronic device 200 is coupled with the mobile communication module 250, and the antenna 2 is coupled with the wireless communication module 260, so that the electronic device 200 can communicate with the network and other devices through wireless communication technology.
  • the wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), broadband Code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC , FM, and/or IR technology, etc.
  • the GNSS may include global positioning system (global positioning system, GPS), global navigation satellite system (global navigation satellite system, GLONASS), Beidou navigation satellite system (beidou navigation satellite system, BDS), quasi-zenith satellite system (quasi -zenith satellite system, QZSS) and/or satellite based augmentation systems (SBAS).
  • global positioning system global positioning system, GPS
  • global navigation satellite system global navigation satellite system, GLONASS
  • Beidou navigation satellite system beidou navigation satellite system, BDS
  • quasi-zenith satellite system quadsi -zenith satellite system, QZSS
  • SBAS satellite based augmentation systems
  • the electronic device 200 implements a display function through a GPU, a display screen 294, an application processor, and the like.
  • the GPU is a microprocessor for image processing, and is connected to the display screen 294 and the application processor.
  • the GPU is used to perform mathematical and geometric calculations for graphics rendering.
  • Processor 210 may include one or more GPUs that execute program instructions to generate or alter display information.
  • Display screen 294 is used to display images, videos, and the like.
  • Display screen 294 includes a display panel.
  • the display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (active-matrix organic light).
  • LED diode AMOLED
  • flexible light-emitting diode flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diode (quantum dot light emitting diodes, QLED) and so on.
  • the electronic device 200 may include one or N display screens 294 , where N is a positive integer greater than one.
  • the electronic device 200 can realize the shooting function through the ISP, the camera 293, the video codec, the GPU, the display screen 294 and the application processor.
  • the ISP is used to process the data fed back by the camera 293 .
  • the shutter is opened, the light is transmitted to the camera photosensitive element through the lens, the light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye.
  • ISP can also perform algorithm optimization on image noise, brightness, and skin tone. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene.
  • the ISP may be provided in the camera 293 .
  • Camera 293 is used to capture still images or video.
  • the object is projected through the lens to generate an optical image onto the photosensitive element.
  • the photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.
  • CMOS complementary metal-oxide-semiconductor
  • the photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal.
  • the ISP outputs the digital image signal to the DSP for processing.
  • DSP converts digital image signals into standard RGB, YUV and other formats of image signals.
  • the electronic device 200 may include 1 or N cameras 293 , where N is a positive integer greater than 1.
  • the camera 293 may be a color camera, and the color camera is used to collect a color image of the target object, including a color camera commonly used in current popular terminal products.
  • the distance sensor 280F is used to obtain the depth information of the target object.
  • the distance sensor 280F can be realized by the Time of Flight (TOF) technology and the structured light technology.
  • TOF technology is that a sensor (such as a depth sensor module) emits modulated near-infrared light, which is reflected after encountering an object.
  • the sensor converts the distance of the captured scene by calculating the time difference or phase difference between light emission and reflection to generate depth information.
  • the three-dimensional outline of the object can be presented in the form of a topographic map with different colors representing different distances.
  • structured light is a system structure composed of projection elements and cameras. After projecting specific light information (such as grating diffraction) onto the surface of the object and the background with the projection element, it is collected by the camera. According to the change of the light signal caused by the object (such as the change and displacement of the light thickness), the information such as the position and depth of the object is calculated; then the entire three-dimensional space is restored.
  • specific light information such as grating diffraction
  • a digital signal processor is used to process digital signals, in addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 200 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy, and the like.
  • Video codecs are used to compress or decompress digital video.
  • Electronic device 200 may support one or more video codecs.
  • the electronic device 200 can play or record videos in various encoding formats, such as: moving picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.
  • MPEG moving picture experts group
  • the NPU is a neural-network (NN) computing processor.
  • NN neural-network
  • Applications such as intelligent cognition of the electronic device 200 can be implemented through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, and the like.
  • the external memory interface 220 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 200.
  • the external memory card communicates with the processor 210 through the external memory interface 220 to realize the data storage function. For example to save files like music, video etc in external memory card.
  • Internal memory 221 may be used to store computer executable program code, which includes instructions.
  • the internal memory 221 may include a storage program area and a storage data area.
  • the storage program area can store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), and the like.
  • the storage data area can store data (such as audio data, phone book, etc.) created during the use of the electronic device 200 and the like.
  • the internal memory 221 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (UFS), and the like.
  • the processor 210 executes various functional applications and data processing of the electronic device 200 by executing instructions stored in the internal memory 221 and/or instructions stored in a memory provided in the processor.
  • the audio module 270 is used for converting digital audio information into analog audio signal output, and also for converting analog audio input into digital audio signal. Audio module 270 may also be used to encode and decode audio signals. In some embodiments, the audio module 270 may be provided in the processor 210 , or some functional modules of the audio module 270 may be provided in the processor 210 .
  • Speaker 270A also referred to as a "speaker" is used to convert audio electrical signals into sound signals.
  • the electronic device 200 can listen to music through the speaker 270A, or listen to a hands-free call.
  • the receiver 270B also referred to as an "earpiece" is used to convert audio electrical signals into sound signals.
  • the voice can be answered by placing the receiver 270B close to the human ear.
  • the microphone 270C also called “microphone” or “microphone” is used to convert sound signals into electrical signals.
  • the user can make a sound by approaching the microphone 270C through the human mouth, and input the sound signal into the microphone 270C.
  • the electronic device 200 may be provided with at least one microphone 270C. In other embodiments, the electronic device 200 may be provided with two microphones 270C, which can implement a noise reduction function in addition to collecting sound signals. In other embodiments, the electronic device 200 may further be provided with three, four or more microphones 270C to collect sound signals, reduce noise, identify sound sources, and implement directional recording functions.
  • the pressure sensor 280A is used to sense pressure signals, and can convert the pressure signals into electrical signals.
  • pressure sensor 280A may be provided on display screen 294.
  • the capacitive pressure sensor may be comprised of at least two parallel plates of conductive material. When a force is applied to pressure sensor 280A, the capacitance between the electrodes changes.
  • the electronic device 200 determines the intensity of the pressure according to the change in capacitance. When a touch operation acts on the display screen 294, the electronic device 200 detects the intensity of the touch operation according to the pressure sensor 280A.
  • the electronic device 200 may also calculate the touched position according to the detection signal of the pressure sensor 280A.
  • touch operations acting on the same touch position but with different touch operation intensities may correspond to different operation instructions. For example, when a touch operation whose intensity is less than the first pressure threshold acts on the short message application icon, the instruction for viewing the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, the instruction to create a new short message is executed.
  • the gyro sensor 280B may be used to determine the motion attitude of the electronic device 200 .
  • the angular velocity of electronic device 200 about three axes ie, x, y, and z axes
  • the gyro sensor 280B can be used for image stabilization.
  • the gyro sensor 280B detects the shaking angle of the electronic device 200, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to counteract the shaking of the electronic device 200 through reverse motion to achieve anti-shake.
  • the gyro sensor 280B can also be used for navigation and somatosensory game scenarios.
  • Air pressure sensor 280C is used to measure air pressure. In some embodiments, the electronic device 200 calculates the altitude through the air pressure value measured by the air pressure sensor 280C to assist in positioning and navigation.
  • the acceleration sensor 280E can detect the magnitude of the acceleration of the electronic device 200 in various directions (generally three axes).
  • the magnitude and direction of gravity can be detected when the electronic device 200 is stationary. It can also be used to identify the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc.
  • the electronic device 200 can measure the distance through infrared or laser. In some embodiments, when shooting a scene, the electronic device 200 can use the distance sensor 280F to measure the distance to achieve fast focusing.
  • the electronic device 200 can use the proximity light sensor 280G to detect that the user holds the electronic device 200 close to the ear to talk, so as to automatically turn off the screen to save power.
  • Proximity light sensor 280G can also be used in holster mode, pocket mode automatically unlocks and locks the screen.
  • the ambient light sensor 280L is used to sense ambient light brightness.
  • the electronic device 200 can adaptively adjust the brightness of the display screen 294 according to the perceived ambient light brightness.
  • the ambient light sensor 280L can also be used to automatically adjust the white balance when taking pictures.
  • the ambient light sensor 280L can also cooperate with the proximity light sensor 280G to detect whether the electronic device 200 is in the pocket, so as to prevent accidental touch.
  • the fingerprint sensor 280H is used to collect fingerprints.
  • the electronic device 200 can use the collected fingerprint characteristics to realize fingerprint unlocking, accessing application locks, taking pictures with fingerprints, answering incoming calls with fingerprints, and the like.
  • the temperature sensor 280J is used to detect the temperature.
  • the electronic device 200 utilizes the temperature detected by the temperature sensor 280J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 280J exceeds a threshold value, the electronic device 200 reduces the performance of the processor located near the temperature sensor 280J in order to reduce power consumption and implement thermal protection.
  • the electronic device 200 heats the battery 242 to avoid abnormal shutdown of the electronic device 200 caused by the low temperature.
  • the electronic device 200 boosts the output voltage of the battery 242 to avoid abnormal shutdown caused by low temperature.
  • the touch sensor 280K is also called “touch device”.
  • the touch sensor 280K may be disposed on the display screen 294, and the touch sensor 280K and the display screen 294 form a touch screen, also called a "touch screen”.
  • the touch sensor 280K is used to detect a touch operation on or near it.
  • the touch sensor can pass the detected touch operation to the application processor to determine the type of touch event.
  • Visual output related to touch operations may be provided through display screen 294 .
  • the touch sensor 280K may also be disposed on the surface of the electronic device 200 , which is different from the location where the display screen 294 is located.
  • the bone conduction sensor 280M can acquire vibration signals.
  • the bone conduction sensor 280M can acquire the vibration signal of the vibrating bone mass of the human voice.
  • the bone conduction sensor 280M can also contact the pulse of the human body and receive the blood pressure beating signal.
  • the bone conduction sensor 280M can also be disposed in the earphone, combined with the bone conduction earphone.
  • the audio module 270 can analyze the voice signal based on the vibration signal of the vocal vibration bone block obtained by the bone conduction sensor 280M, so as to realize the voice function.
  • the application processor can analyze the heart rate information based on the blood pressure beat signal obtained by the bone conduction sensor 280M, so as to realize the function of heart rate detection.
  • Motor 291 can generate vibrating cues.
  • the motor 291 can be used for vibrating alerts for incoming calls, and can also be used for touch vibration feedback.
  • touch operations acting on different applications can correspond to different vibration feedback effects.
  • the motor 291 can also correspond to different vibration feedback effects for touch operations on different areas of the display screen 294 .
  • Different application scenarios for example: time reminder, receiving information, alarm clock, games, etc.
  • the touch vibration feedback effect can also support customization.
  • the SIM card interface 295 is used to connect a SIM card.
  • the SIM card can be contacted and separated from the electronic device 200 by inserting into the SIM card interface 295 or pulling out from the SIM card interface 295 .
  • the electronic device 200 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1.
  • the SIM card interface 295 can support Nano SIM card, Micro SIM card, SIM card and so on.
  • the same SIM card interface 295 can insert multiple cards at the same time.
  • the types of the plurality of cards may be the same or different.
  • the SIM card interface 295 can also be compatible with different types of SIM cards.
  • the SIM card interface 295 is also compatible with external memory cards.
  • the electronic device 200 interacts with the network through the SIM card to realize functions such as call and data communication.
  • the electronic device 200 employs an eSIM, ie: an embedded SIM card.
  • the eSIM card can be embedded in the electronic device 200 and cannot be separated from the electronic device 200 .
  • the 3D model reconstruction tool includes IDE and AR Cloud. Among them, users can upload photos, view execution progress, preview 3D models, etc. through the IDE; AR Cloud is used to perform 3D model reconstruction and calculation process to generate 3D models.
  • an embodiment of the present application provides a 3D model reconstruction scheme.
  • the user submits the quality expectation of the 3D model, and according to the user's quality expectation of the 3D model, an image acquisition scheme is generated, and the user is instructed to carry out Photo acquisition of reconstructed objects.
  • the quality of the photos collected under the guidance of the image collection scheme is higher, and the success rate of one-time reconstruction is improved.
  • the effect of 3D model reconstruction can also be estimated in advance according to the photos collected by the user. Only after the effect of the 3D model reconstruction meets the user's quality expectations, the 3D model reconstruction process is performed to further improve the success rate of one-time reconstruction.
  • FIG. 3 a schematic diagram of a 3D model reconstruction scene according to an embodiment of the present application is provided.
  • an animal model toy is used as an example to briefly introduce the 3D model reconstruction scene provided by the embodiment of the present application.
  • Fig. 3A is a reconstruction object
  • the reconstruction object is an animal model toy owned by the user
  • the user wishes to reconstruct the 3D model of the animal model toy
  • the 3D model the user wishes to reconstruct is the 3D model corresponding to the animal model toy
  • the user submits quality expectations for the 3D model. For example, the user wishes to build a 3D model with 1000 faces, a mean square error (MSE) within 2mm, and a diameter within 10cm. Among them, the number of faces is used to describe the number of polygons that make up the 3D model.
  • MSE mean square error
  • MSE is used to describe the average difference between the points of the 3D model after modeling and the points corresponding to the actual object.
  • Diameter is used to describe the diameter of the sphere corresponding to the 3D model, that is, the size of the 3D model can be measured by the size of the sphere corresponding to the 3D model.
  • the length, width and height of the 3D model can also be used to measure the size of the 3D model.
  • Figure 3B shows the image acquisition scheme generated by AR Cloud according to the user's quality expectation. After the user submits the quality expectation of the 3D model to AR Cloud, AR Cloud generates a corresponding image acquisition scheme according to the quality expectation.
  • the image acquisition scheme requires the user to take 24 photos at a distance of 60 cm from the animal model toy, from 8 angles, and in 3 levels in height.
  • Figure 3E shows the 3D model reconstructed by AR Cloud. After AR Cloud completes the reconstruction of the 3D model, it sends the reconstructed 3D model to the terminal device. The user obtains the 3D model of the animal model toy and completes the reconstruction of the 3D model.
  • a reconstruction communication link is added in the 3D model reconstruction process, and the 3D model reconstruction requirements and the image acquisition scheme are communicated, so as to avoid the problem that the 3D model reconstruction fails due to the collected two-dimensional images that do not meet the 3D model reconstruction requirements. Improve the success rate of a reconstruction.
  • FIG. 4 it is a schematic flowchart of a method for reconstructing a three-dimensional model according to an embodiment of the present application. The method can be applied to the device shown in FIG. 1 , as shown in FIG. 4 , which mainly includes the following steps.
  • Step S401 The terminal device sends the three-dimensional model reconstruction index information to the server device.
  • the three-dimensional model reconstruction index information is used to represent the three-dimensional model reconstruction requirements.
  • the three-dimensional model reconstruction index information includes quality index information and/or object index information of the 3D model.
  • the quality index information is used to characterize the quality of the 3D model to be reconstructed
  • the object index information is used to characterize the size of the 3D model to be reconstructed.
  • the quality of the 3D model includes indicators such as the accuracy, completeness, and consistency of the 3D model, which can be determined by means of mean square error (MSE) and/or intersection over union (IoU) measure.
  • MSE is used to describe the average difference between the points of the modeled 3D model and the corresponding points of the actual object
  • IoU is used to describe the ratio of the intersection and union of the modeled 3D model and the actual object.
  • the quality index information is related to the number of faces of the 3D model after modeling. The higher the quality index, the more faces of the 3D model after modeling. The higher the number, the smoother the model and the richer the details. Understandably, the higher the quality index, the more photos the user needs to collect and the higher the quality, the longer the 3D model reconstruction takes, and the more computing resources are consumed, including memory and processor resources.
  • the size of the 3D model can be represented by the length, width and height of the 3D model; on the other hand, the size of the 3D model can be represented by the diameter of the sphere corresponding to the 3D model. It is understandable that the larger the size of the 3D model, the more photos the user needs to collect and the higher the quality. The process of generating the 3D model from the 2D image will take longer and consume more computing resources.
  • FIGS. 5A-5D it is a schematic diagram of a three-dimensional model reconstruction index configuration scene according to an embodiment of the present application.
  • the terminal device Before the terminal device sends the 3D model reconstruction index information to the server device, the terminal device displays the 3D model reconstruction index configuration window, and the user can input the desired quality index and/or object index at the corresponding position inside the window, and perform the 3D model reconstruction index.
  • the information input by the user in this window is the 3D model reconstruction index input information.
  • the user inputs in the input area of the window: "IoU, 99%; object size, 8cm".
  • IoU is used to describe the quality index.
  • MSE MSE
  • IoU to describe the quality index.
  • This application implements The example does not limit this.
  • the quality index can also be divided into three options of high, medium and low according to the interval for the user to choose. For example, at the quality index, the user inputs: "quality index, high" without inputting a specific numerical value of the quality index.
  • the 3D model reconstruction index information may also include performance index information, where the performance index information is used to represent the resources expected by the user in the 3D model reconstruction process, and the resources expected by the user include the time expected by the user resources and/or computing resources. For example, the expected time spent and/or the computing resources expected to be used, including memory, processor resources, and the like. For example, the user hopes to complete the 3D model reconstruction within 6 hours, occupying 1.8G of system memory and a single-core processor.
  • the performance index information is the user's expectation of resource consumption during the 3D model reconstruction process.
  • a series of preset 3D model reconstruction indicators can be displayed in the 3D model reconstruction indicator configuration window.
  • the user can select the 3D model reconstruction indicator according to needs, that is, input the 3D model reconstruction indicator in the 3D model reconstruction indicator configuration window.
  • the model rebuilds the indicator selection information to complete the indicator configuration.
  • the user selects the configuration information of "quality index, medium; object size, 10-50cm; time-consuming, 6 hours; memory, 1.6G; processor, dual-core" by clicking on the corresponding position in the window,
  • the terminal device sends the configuration information to AR Cloud.
  • FIGS. 5A-5D are only exemplary illustrations, and those skilled in the art can adjust the configuration of the three-dimensional model reconstruction index information accordingly according to actual needs.
  • the performance indicator in addition to the number of cores of the processor, the main frequency value of the processor can also be configured; the corresponding computing resources in different tariff packages can also be adjusted according to actual needs.
  • Step S402 The server device determines an image acquisition scheme according to the three-dimensional model reconstruction index information.
  • the server device after receiving the three-dimensional model reconstruction index information, determines an image acquisition scheme that can meet the requirements of the three-dimensional model reconstruction index.
  • the collection of photos is a very important step in the whole 3D model reconstruction process, and the quality of the reconstruction results often has a great relationship with the collected photos. It can be understood that in order to achieve different quality indicators and/or object indicators, the required quantity and quality of photos are also different.
  • the image acquisition scheme may include the number of photos, angles, distances, resolutions, lighting conditions, background requirements, and the like. A detailed description will be given below.
  • each part of the reconstructed object should be photographed from multiple different viewpoints.
  • photos taken around the reconstructed object should ensure a certain overlapping area, and different quality indicators and/or object indicators have different requirements for the overlapping area. Since the number and angle of photos will affect the size of the overlapping area, different quality metrics and/or object metrics require different numbers of photos and shooting angles.
  • FIGS. 6A-6C it is a schematic diagram of an image acquisition scene provided by an embodiment of the present application.
  • Fig. 6A shows the image acquisition device 601 and the reconstructed object 602.
  • the image acquisition device 601 takes pictures around the reconstructed object 602 from 8 viewing angles, and takes 8 photos, wherein the At two adjacent shooting angles, overlapping image acquisition areas form overlapping areas. That is to say, there are overlapping parts in the two photos captured at two adjacent shooting angles.
  • the image capture device 601 captures around the reconstructed object 602 from 16 viewing angles, and captures 16 photos.
  • the overlapping area of the photos collected according to the image collection scheme on the left side of FIG. 6A accounts for a small proportion; the overlapping area of the photos collected according to the image collection scheme on the right side of FIG. 6A accounts for a relatively large proportion. Therefore, when the quality index and/or object index of the 3D model reconstruction is required to be high, more photos should be taken, and the angles between different photos should be reasonably controlled to obtain a higher proportion of overlapping areas.
  • angles involved in the embodiments of the present application include, in addition to relative angles between different shooting angles of view in the same horizontal plane, shooting angles at different heights. Especially for reconstructed objects with a certain height, it is necessary to perform image acquisition from different heights.
  • the image acquisition device 601 performs image acquisition in three layers from the height direction, namely the first layer, the second layer and the third layer.
  • the shooting angle of view and the shooting quantity of each layer reference may be made to the description in FIG. 6A , and details are not described herein again in this embodiment of the present application.
  • the image acquisition device 601 performs image acquisition relative to the reconstructed object 602 from far to near and from different distances in three layers, namely the first layer, the second layer and the third layer.
  • This method can restore the texture information of the reconstructed photo to the greatest extent. Therefore, for the reconstructed object with high quality index requirements, it should be photographed in layers from far to near and from different distances.
  • the quality of the reconstructed 3D model is directly related to the resolution of the captured photos, therefore, the higher the quality index is, the higher the resolution of the captured photos is correspondingly.
  • photos of different resolutions may be collected through cameras of different resolutions.
  • the image acquisition equipment includes a 500M resolution camera and a 1000M resolution camera. When the quality index is high, the 1000M resolution camera is used for image acquisition; when the quality index is low, the 500M resolution camera is used for image acquisition.
  • a stable ambient light source will improve the quality of the captured photos.
  • the quality index and/or object index of 3D model reconstruction is required to be high, it should be ensured that the lighting condition is a stable ambient light source.
  • the background of different photos should be kept uniform and not too cluttered, so as not to affect the 3D model reconstruction. It should be pointed out that, for a reconstructed object with a relatively single texture, a background pattern needs to be added within the shooting range, so that the relative positions of the photos taken from different angles are different.
  • the server device can estimate through an algorithm to generate an image acquisition scheme.
  • the three-dimensional model reconstruction index information can be used as an input parameter of the preset algorithm model, and after the three-dimensional model reconstruction index information is input into the algorithm model, an image acquisition scheme is output.
  • This embodiment of the present application does not specifically limit the algorithm model.
  • the image acquisition scheme may be determined by searching a preset image acquisition scheme comparison table.
  • the image acquisition scheme comparison table can be pre-configured according to experience, including quality indicators, object indicators, image acquisition schemes, and their corresponding relationships.
  • the quality indicators are divided into three categories according to the interval. For example, in the quality indicator information sent by the terminal equipment, if IoU>98%, it means the quality indicator is "high”; if 95% ⁇ IoU ⁇ 98%, It means the quality index is "medium”; if 90% ⁇ IoU ⁇ 95%, it means the quality index is "low”.
  • the size of the object is described by the size of the sphere corresponding to the 3D model, and is divided into three intervals according to the diameter of the corresponding sphere, smaller than 10 cm, 10-50 cm, and larger than 50 cm.
  • the system pre-defined five camera positions A, B, C, D, and E.
  • the camera is an image acquisition scheme, and different camera positions represent different photographing requirements. E.g:
  • Camera position A means using a 200M resolution camera, shooting from 4 positions around the reconstructed object, and requiring a light intensity of more than 200 lumens.
  • lumen is the physical unit that describes the luminous flux.
  • Camera position B means using a 500M resolution camera, shooting from 4 positions around the reconstructed object, and requiring a light intensity of more than 300 lumens.
  • Camera position C means using a camera with a resolution of more than 1000M, and shooting from 4 positions around the reconstructed object.
  • the reconstructed object is required to occupy more than 60% of the screen, and the light intensity is 500 lumens.
  • the distance between the image acquisition device and the reconstructed object can be reflected by the proportion of the reconstructed object in the photo frame.
  • Camera position D means using a camera with a resolution of more than 1000M, shooting from 16 positions around the reconstructed object, requiring the object to occupy more than 60% of the screen, and the light intensity at 500 lumens.
  • Camera position E means using a camera with a resolution of 1000M or above, and shooting from 24 positions around the reconstructed object.
  • the object is required to occupy more than 60% of the screen, and the light intensity is 500 lumens.
  • AR Cloud can also generate estimated performance information based on quality index information and object index information.
  • the estimated performance information is used to represent the estimated resources to be consumed during the reconstruction of the three-dimensional model, and the estimated to be consumed resources includes the estimated time resources and/or computing resources to be consumed.
  • computing resources may include memory and/or processor resources, among others.
  • the estimated performance information can also be pre-configured in the image acquisition scheme comparison table at the same time, and the estimated performance information corresponding to the quality index information and the object index information is determined by looking up the table, as shown in Table 2.
  • the performance index information in the 3D model reconstruction index information is the performance information expected by the user
  • the estimated performance information generated by AR Cloud is the performance information estimated by AR Cloud based on the quality index and object index.
  • AR Cloud compares the estimated performance information with the performance information expected by the user to determine whether the performance information expected by the user can meet the requirements for 3D model reconstruction. If the 3D model reconstruction requirements can be met, the computing resources are allocated according to the performance information expected by the user; if the 3D model reconstruction requirements cannot be satisfied, the computing resources are allocated according to the estimated performance information.
  • AR Cloud can also send its estimated performance information to the terminal device for the user to confirm or select.
  • AR Cloud can allocate the corresponding computing resources according to the time resources expected by the user; when the performance index information expected by the user only includes computing resources, AR Cloud can allocate computing resources according to the user's expected
  • the estimated time resource of the computing resources that is, the estimated time required, and the estimated time is sent to the terminal device for the user's reference.
  • Step S403 The server device sends the image acquisition scheme to the terminal device.
  • the server device after the server device generates an image acquisition scheme, it sends the image acquisition scheme to the terminal device, so that the terminal device can perform image acquisition according to the image acquisition scheme.
  • Step S404 The terminal device acquires a two-dimensional image of the reconstructed object according to the image acquisition scheme.
  • the image acquisition solution may be specific image acquisition guidance information, such as text-based image acquisition guidance information, and the user takes photos according to the instructions of the text-based image acquisition guidance information.
  • This process is a manual configuration process. For example, the user sets the background and lighting conditions by themselves according to the description of the image acquisition scheme, and the handheld image acquisition device shoots around the reconstructed object to obtain a two-dimensional image of the reconstructed object.
  • the image collection solution can also collect guide information for audio and video images, such as a video tutorial, which can guide the user to shoot in the form of pictures, text and sounds.
  • guide information for audio and video images such as a video tutorial, which can guide the user to shoot in the form of pictures, text and sounds.
  • the image acquisition scheme can also be a readable file for the terminal device.
  • an image acquisition guide program is generated on the terminal device, and the user is guided to shoot through the guide program, so as to improve the convenience and efficiency of image acquisition. accuracy. It can be understood that when the user is guided to shoot through the guide program, the guide program also needs to perform illumination detection and background detection to determine whether the illumination conditions or the background meet the requirements of the image acquisition scheme.
  • the image acquisition guidance program includes movement direction guidance information, and the movement direction guidance information is used to prompt movement to the target position, so as to improve the friendliness of human-computer interaction.
  • FIGS. 7A-7C it is a schematic diagram of an image acquisition guidance scene according to an embodiment of the present application.
  • An image capture window is provided in the display interface shown in FIGS. 7A-7C , and the image capture window includes an image capture frame (dotted line frame) 701 and a guide arrow 702 , the guide arrow 702 is moving direction guide information.
  • the image capture frame 701 displays the image information corresponding to the camera in real time, and the guide arrows 702 around the image capture frame 701 are used to guide the moving direction of the terminal device.
  • the terminal device detects that the user has turned to the second image capture point , the arrow on the right side of the image capture frame 701 returns to normal, and the terminal device captures the second photo at this position, as shown in FIG. 7C .
  • the terminal device completes the collection of all photos.
  • the user is guided to move the terminal device to the target position through the moving direction guidance information, which facilitates the user's operation and improves the friendliness of human-computer interaction.
  • the image collection guide program further includes an image collection sequence, and guides the user to complete the collection of 2D images according to the image collection sequence. . Specifically, after the first two-dimensional image collection of the first collection position is completed, the moving direction guidance information from the first collection position to the second collection position is output, and the movement direction guidance information from the first collection position to the second collection position is output. Used to prompt movement to the second collection position.
  • the embodiment of the present application does not limit the specific form of the moving direction guidance information.
  • it may also be voice guide information, or other types of indication information in the display interface.
  • the image acquisition guidance program includes a three-dimensional image acquisition scene, in which a position where two-dimensional image acquisition needs to be performed is marked. It can be understood that the position of the mark is the target position, the user can determine the moving direction of the terminal device through the position of the mark, and the position of the mark is the movement direction guidance information. 8A-8E will be described in detail below. In FIGS. 8A-8E , the position where two-dimensional image acquisition needs to be performed is marked by the image acquisition positioning frame.
  • FIGS. 8A-8E another schematic diagram of an image acquisition guidance scene provided by an embodiment of the present application.
  • An image acquisition box (dashed box) 801, an image acquisition positioning box (solid box) 802, and a guide arrow 803 are shown in Figures 8A-8E.
  • the reconstructed object remains stationary, and the terminal device surrounds the reconstructed object 360° and shoots from multiple different perspectives.
  • the gyroscope sensor and the acceleration sensor in the terminal device can detect the rotation angle and/or the moving distance of the terminal device in real time, and then make the image acquisition and positioning frame 802 rotate the corresponding angle and/or Move the corresponding distance.
  • the moving direction of the image capturing and positioning frame 802 in the display interface is opposite to the moving direction of the terminal device.
  • the image capture positioning frame 802 moves to the left in the display interface.
  • the guide arrow 803 is used to indicate the moving direction of the image capturing and positioning frame 802 in the display interface.
  • the guide arrow 803 may not be included, which is not limited in the embodiment of the present application.
  • the user can judge the moving direction of the terminal device and determine the terminal device through the relative positions of the image capture frame 801 and the image capture positioning frame 802 whether to move to the corresponding position.
  • the terminal device is controlled to take pictures, so as to obtain a photo at the image capturing angle of view.
  • the shooting action may be automatically triggered by the terminal device, or may be triggered by the user, which is not limited in this embodiment of the present application.
  • the guide program includes multiple image capture positioning frames 802, each image capture positioning frame 802 represents a shooting angle of view, and the guide program presets the position of each image capture positioning frame 802 according to the image capture scheme. For example, in the embodiment shown in FIGS. 8A-8E , it is necessary to collect 8 photos evenly around the reconstructed object, that is, to collect a photo every 45° around the reconstructed object.
  • the guide program includes 8 image capturing and positioning frames 802 , the eight image capturing and positioning frames 802 circle around, and the interval between adjacent image capturing and positioning frames 802 is 45°.
  • each image acquisition and positioning frame 802 is provided with a number. Positioning frame 2 and image acquisition positioning frame 8.
  • the image capture positioning frame 1 matches the image capture frame 801 , and at this time, the terminal device is triggered to capture the first photo.
  • the terminal device rotates to the right, and accordingly, the image acquisition positioning frame 802 rotates to the left in the screen (as shown by the arrow in FIG. 8B ), and moves to the position shown in FIG. 8B , At this time, the image capture positioning frame 2 has not moved to a position matching the image capture frame 801 .
  • the terminal device continues to move to the right, and the image capture positioning frame 2 continues to move to the left on the screen to the position shown in Figure 8C. At this time, the image capture positioning frame 2 matches the image capture frame 801, triggering the terminal device to capture the second a photograph.
  • the user completes the acquisition of all photos according to the instructions of the image acquisition positioning box 802 in the guide program.
  • the terminal device can judge by itself whether to move to the target position.
  • the terminal device determines that it has moved to the target position, it outputs the prompt information of reaching the target position, so as to avoid the user from triggering the image acquisition action of the terminal device when the target position is not reached or exceeds the target position, which affects the quality of the collected two-dimensional image.
  • the prompt information for reaching the target position may be voice prompt information, indication information in a display interface or an indicator light, etc., which is not specifically limited in this embodiment of the present application.
  • the terminal device can detect the rotation angle and/or the moving distance of the terminal device in real time through the gyroscope sensor and the acceleration sensor, and then determine whether to move to the target position.
  • a preview image of the acquired 2D image can be displayed in real time on the display interface, so that the user can know the 2D image acquisition progress in real time.
  • the user can also check according to the preview image to avoid the omission of the two-dimensional image.
  • the preview image of the captured photo is displayed at the position of the image capture positioning frame 1, which can facilitate the user to understand the progress of the image capture.
  • the display screen of the terminal device is divided into an image preview window and an image acquisition window, as shown in FIG. 8E .
  • the positioning frame in the image preview window is referred to as the image preview positioning frame 804 .
  • the schematic diagram of the entire image acquisition scheme is displayed in the image preview window, including the number of the image preview positioning frames 804 and the position of the image preview positioning frames 804 .
  • the current image acquisition progress can also be displayed in the image preview window. Specifically, at the position of the image preview positioning frame 804 after the acquisition is completed, a preview image of the acquired photo is displayed. As shown in FIG.
  • a preview of the collected photos is displayed in the image preview window, at the positions of the image preview positioning frame 1 and the image preview positioning frame 2 image.
  • a fixed image can be displayed in the image preview window (the image preview positioning frame 804 in the image preview window does not move or rotate correspondingly with the movement or rotation of the terminal device), or a moving image can be displayed (image preview The image preview positioning frame 804 in the window moves or rotates correspondingly with the movement or rotation of the terminal device), which is not limited in this embodiment of the present application.
  • the image acquisition manner in the image acquisition window is similar to the image acquisition manner described in the embodiment shown in FIGS. 8A-8D , and details are not described herein again.
  • the image acquisition guide program guides the user to manually complete the acquisition of two-dimensional images.
  • a robotic arm is controlled by the image acquisition guide program to drive the terminal device to move to a target position, and a two-dimensional image of the reconstructed object is acquired.
  • the acquisition of two-dimensional images by a robotic arm can be controlled more precisely, and the acquisition accuracy of two-dimensional images is higher.
  • FIG. 9 it is a schematic flowchart of another three-dimensional model reconstruction method according to an embodiment of the present application. As shown in FIG. 9 , the method further includes the following steps after step S404 in the embodiment shown in FIG. 4 .
  • Step S901 The terminal device preprocesses the collected two-dimensional image to obtain summary information of the two-dimensional image.
  • the terminal device preprocesses the collected photos, and generates summary information of the collected photos, where the summary information is used to judge whether the collected photos meet the requirements for the photos in the image collection scheme.
  • requirements that is, whether the 3D model reconstruction requirements are met.
  • the summary information includes the number of photos, a collection angle of each photo, a low-resolution version of the photo, and the like.
  • Step S902 The terminal device sends the summary information of the two-dimensional image to the server device.
  • the terminal device After obtaining the abstract information of the two-dimensional image, the terminal device sends the abstract information to the server device, so that the server device can judge whether the photos collected by the terminal device can meet the requirements of 3D model reconstruction according to the abstract information.
  • Step S903 The server device determines, according to the summary information of the two-dimensional image, whether the collected two-dimensional image set meets the three-dimensional model reconstruction requirements.
  • the server device may determine, according to the summary information, the number of photos collected by the terminal device, and whether the quality of each photo meets the requirements.
  • the evaluation indicators of the quality of a photo include resolution, illumination, saturation, sharpness, the proportion of reconstructed objects in the photo, the shooting angle, and the background color.
  • Step S904 If the collected two-dimensional image meets the three-dimensional model reconstruction requirements, send an instruction that the two-dimensional image meets the condition to the terminal device.
  • the server device determines that the two-dimensional image collected by the terminal device meets the requirements for three-dimensional model reconstruction, indicating that the three-dimensional model reconstruction that meets the requirements of the quality index and the object index can be completed within a corresponding time, it sends a two-dimensional image to the terminal device.
  • the dimensional image satisfies the conditional directive.
  • the server device After receiving the instruction that the two-dimensional image satisfies the condition, the server device sends the collected two-dimensional image to the server device, so that the server device can perform the 3D model reconstruction operation.
  • Step S905 If the acquired two-dimensional image does not meet the three-dimensional model reconstruction requirements, generate an image supplementary acquisition scheme.
  • the server device determines that the 2D image collected by the terminal device does not meet the requirements for 3D model reconstruction, it means that the 3D model reconstruction that meets the quality index and object index requirements cannot be completed within a corresponding time using the collected 2D image. , and the server device generates an image supplementary acquisition scheme according to the summary information.
  • the terminal device is required to collect 8 photos, but the server device determines that only 7 photos are collected by the terminal device according to the summary information. Therefore, it can be determined that the number of photos collected by the terminal device does not meet the requirements, and the photos need to be checked. Supplementary collection.
  • Step S906 The server device sends the image supplementary acquisition scheme to the terminal device.
  • the server device After generating the supplementary image acquisition scheme, the server device sends the supplementary image acquisition scheme to the terminal device, so that the terminal device supplementally acquires two-dimensional images according to the supplementary image acquisition scheme.
  • the image supplemental acquisition scheme may be an image supplementary acquisition guide program, text-based image supplemental acquisition guidance information, and/or audio-video image supplemental acquisition guidance information, for example, a shooting tutorial, which may be in the form of images, texts, and sounds. way to guide the user to shoot.
  • a shooting tutorial which may be in the form of images, texts, and sounds. way to guide the user to shoot.
  • the image supplementary acquisition scheme includes defect prompt information, where the defect prompt information is used to prompt the user for the reason of the defect, so as to facilitate the user to supplement the acquisition of the two-dimensional image.
  • FIG. 10 it is a schematic diagram of a supplementary image acquisition scheme provided by an embodiment of the present application.
  • the image acquisition scheme requires that the proportion of reconstructed objects in the acquired photos should be greater than 60%.
  • the proportion of reconstructed objects in the acquired photos should be greater than 60%.
  • the server device sends the image supplementary acquisition scheme to the terminal device.
  • the supplementary image acquisition scheme includes two-dimensional images that do not meet the requirements, and the reason that the two-dimensional images do not meet the requirements "the proportion of reconstructed objects in the photo is less than 60%", as shown in Figure 10. Based on the above information, the user can easily determine the 2D images that need to be supplemented and collected, as well as the precautions for supplementary acquisition of 2D images, so as to ensure that the supplementary 2D images meet the requirements of the supplementary image acquisition scheme.
  • FIG. 11 it is a schematic diagram of another image supplementary acquisition scheme provided in this embodiment of the present application.
  • a two-dimensional image is shown in Fig. 11, the two-dimensional image is overexposed and does not meet the requirements of 3D model reconstruction, and an image supplementary acquisition scheme is generated.
  • the server device sends the image supplementary acquisition scheme to the terminal device.
  • the image supplementary acquisition scheme includes a 2D image that does not meet the requirements, and the reason for the 2D image that does not meet the requirements "photo overexposed".
  • the user can easily determine the 2D images that need to be supplemented and the precautions for supplementary acquisition of 2D images, for example, reduce the light intensity in the shooting environment, or adjust the aperture of the camera to reduce the exposure, Make sure that the 2D image of the supplemental acquisition meets the requirements of the image supplementary acquisition protocol.
  • the two-dimensional image collected by the terminal device may also have other defects, for example, the resolution is too low, the photo background does not meet the requirements, etc., which will not be listed here.
  • Step S907 The terminal device supplementally acquires the two-dimensional image of the reconstructed object according to the image supplementary acquisition scheme.
  • the terminal device After receiving the supplementary image acquisition scheme, the terminal device supplementally acquires the two-dimensional image of the reconstructed object according to the supplementary image acquisition scheme. After completing the image supplementary acquisition, the acquired two-dimensional image is sent to the server device.
  • the 2D images collected at this time include the 2D images initially collected by the terminal device according to the image collection scheme, and the 2D images supplementarily collected according to the image collection scheme.
  • the terminal device may also send the summary information of the supplementary collected two-dimensional image to the server device, and the server device determines whether the supplementary two-dimensional image is collected or not. fulfil requirements.
  • the terminal device and the server device further communicate the quantity and quality of the acquired two-dimensional images, which can further improve the success rate of one-time reconstruction.
  • Step S1201 The terminal device sends the collected two-dimensional image to the server device.
  • the terminal device After completing the image acquisition, the terminal device sends the acquired two-dimensional image to the server device, so that the server device can perform a 3D model reconstruction operation according to the two-dimensional image.
  • the two-dimensional image sent by the terminal device to the server device includes the two-dimensional image initially collected by the terminal device according to the image acquisition scheme, and the supplementary acquisition scheme according to the image. Supplementary acquired 2D images.
  • the server device After receiving the two-dimensional image sent by the terminal device, the server device performs a 3D model reconstruction operation on the two-dimensional image to generate a 3D model.
  • the 3D model reconstruction operation may be a photogrammetry pipeline calculation.
  • the embodiment of the present application does not limit the 3D model reconstruction tool, and those skilled in the art can complete the 3D model reconstruction based on other tools.
  • the progress of the 3D model reconstruction may be sent to the terminal device at preset time intervals, so that the user can grasp the progress of the 3D model reconstruction in real time.
  • Step S1203 The server device sends the three-dimensional model to the terminal device.
  • the server device After completing the reconstruction of the 3D model, the server device sends the 3D model to the terminal device. At this point, the reconstruction of the 3D model is completed.
  • the 3D model can be a 3D model-specific format file such as obj. This file can then be used for 3D printing, animation production, teaching, product design and other processes.
  • an embodiment of the present application further provides a terminal device, where the terminal device includes one or more cameras, a processor, a memory, and one or more computer programs, wherein the one or more computer programs are Stored in the memory, the one or more computer programs include instructions that, when executed by the terminal device, cause the terminal device to perform some or all of the steps in the above method embodiments.
  • an embodiment of the present application further provides a server device, where the server device includes one or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in In the memory, the one or more computer programs include instructions, which, when executed by the terminal device, cause the terminal device to perform some or all of the steps in the above method embodiments.
  • the present application further provides a computer storage medium, wherein the computer storage medium can store a program, and when the program is executed, it can include some or all of the steps in the various embodiments provided in the present application.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (English: read-only memory, abbreviated as: ROM) or a random access memory (English: random access memory, abbreviated as: RAM) and the like.
  • an embodiment of the present application further provides a computer program product, where the computer program product includes executable instructions, and when the executable instructions are executed on a computer, enables the computer to execute part or some of the above method embodiments. all steps.
  • “at least one” refers to one or more, and “multiple” refers to two or more.
  • “And/or”, which describes the association relationship of the associated objects means that there can be three kinds of relationships, for example, A and/or B, which can indicate the existence of A alone, the existence of A and B at the same time, and the existence of B alone. where A and B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an “or” relationship.
  • “At least one of the following” and similar expressions refer to any combination of these items, including any combination of single or plural items.
  • At least one of a, b, and c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c may be single or multiple.
  • any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM for short), random access memory (RAM for short), magnetic disk or optical disk, etc. that can store program codes medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本申请实施例提供的一种三维模型重建方法、设备和存储介质，所述方法包括向服务器设备发送三维模型重建指标信息，所述三维模型重建指标信息用于表征三维模型重建要求；接收所述服务器设备发送的图像采集方案，所述图像采集方案用于指导重建对象的二维图像的采集；根据所述图像采集方案，采集重建对象的二维图像，所述二维图像用于三维模型重建。本申请实施例中在3D模型重建过程中增加重建沟通环节，对3D模型重建要求和图像采集方案进行沟通，避免采集的二维图像不符合3D模型重建要求，而引起的3D模型重建失败的问题，提高一次重建成功率。

Description

三维模型重建方法、设备和存储介质
本申请要求于2020年12月25日提交中国专利局、申请号为202011585146.9、申请名称为“三维模型重建方法、设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，具体地涉及一种三维模型重建方法、设备和存储介质。
背景技术
三维(3 Dimensional，3D)模型重建是指根据单视图或者多视图的图像建立适合计算机标识和处理的数学模型的过程，是在计算机中建立、表达客观世界的关键技术，可广泛应用于反向工程、游戏、购物、教学等场景中。
相关技术中一种3D模型重建方法主要包括以下步骤：步骤S101，通过图像采集设备从不同角度、不同距离采集重建对象的二维图像，图像采集过程中重建对象固定，仅移动图像采集设备；步骤S102，对采集的二维图像进行特征提取、图像匹配、特征匹配、立体结构、景深估计、网格化、增加纹理、定位等处理，获得重建对象对应的3D模型。
但是，上述步骤S102中，由二维图像生成3D模型的过程非常耗时，若重建的3D模型达不到用户的质量要求则需要重新进行3D模型重建，浪费用户时间，用户体验较差。
发明内容
有鉴于此，本申请提供一种三维模型重建方法、设备和存储介质，以利于解决现有技术中3D模型重建方案浪费用户时间，用户体验较差的问题。
第一方面，本申请实施例提供了一种三维模型重建方法，所述方法包括：向服务器设备发送三维模型重建指标信息，所述三维模型重建指标信息用于表征三维模型重建要求；接收所述服务器设备发送的图像采集方案，所述图像采集方案用于指导重建对象的二维图像的采集；根据所述图像采集方案，采集所述重建对象的二维图像，所述二维图像用于三维模型重建。
本申请实施例在3D模型重建过程中增加重建沟通环节，对3D模型重建要求和图像采集方案进行沟通，避免采集的二维图像不符合3D模型重建要求，而引起的3D模型重建失败的问题，提高一次重建成功率。
在一种可能的实现方式中，所述图像采集方案包括图像采集引导程序；所述根据 所述图像采集方案，采集重建对象的二维图像，包括：根据所述图像采集引导程序的引导，采集所述重建对象的二维图像。
在本申请实施例中，通过图像采集引导程序引导二维图像的采集，提高二维图像采集的便捷性及准确性。
在一种可能的实现方式中，所述根据所述图像采集引导程序的引导，采集所述重建对象的二维图像，包括：输出移动方向指引信息，所述移动方向指引信息用于提示向目标位置移动；响应于用户输入的图像采集指令，采集所述重建对象的二维图像。
在本申请实施例中，通过移动方向指引信息指引终端设备向目标位置移动，便于用户操作，提高人机交互的友好性。
在一种可能的实现方式中，所述图像采集引导程序包括图像采集顺序，所述输出移动方向指引信息，包括：根据所述图像采集顺序，在完成第一采集位置的第一二维图像采集后，输出第一采集位置至第二采集位置的移动方向指引信息，所述第一采集位置至第二采集位置的移动方向指引信息用于提示向第二采集位置移动。
在本申请实施例中，便于用户按照预设的图像采集顺序，依次完成所有二维图像的采集，提高二维图像的采集效率，且避免二维图像的遗漏。
在一种可能的实现方式中，所述方法还包括：当判断移动至所述目标位置时，输出到达目标位置提示信息。
在本申请实施例中，当终端设备移动至目标位置时，输出到达目标位置提示信息，避免用户在未到达目标位置或超过目标位置时触发终端设备的图像采集动作，影响采集的二维图像的质量。
在一种可能的实现方式中，所述根据所述图像采集引导程序的引导，采集所述重建对象的二维图像，包括：通过所述图像采集引导程序控制机械臂带动所述终端设备移动至目标位置，采集所述重建对象的二维图像。
在本申请实施例中，通过机械臂进行二维图像的采集可以进行更加精准的控制，二维图像的采集精度更高。
在一种可能的实现方式中，所述方法还包括：展示完成采集的二维图像的预览图像。
在本申请实施例中，展示已经完成采集的二维图像的预览图像，可以便于用户实时了解二维图像的采集进度。另外，用户还可以根据该预览图像进行核查，避免二维图像的遗漏。
在一种可能的实现方式中，所述方法还包括：对采集的所述二维图像进行预处理，获得所述二维图像的摘要信息；向所述服务器设备发送所述二维图像的摘要信息，所述摘要信息用于判断采集的所述二维图像是否满足三维模型的重建要求；响应于所述服务器设备发送的图像补充采集方案，根据所述图像补充采集方案，补充采集所述重建对象的二维图像；或者，接收所述服务器设备发送的二维图像满足条件指令，所述二维图像满足条件指令用于表征采集的所述二维图像可以满足三维模型的重建要求。
在本申请实施例中，根据图像采集方案完成二维图像的采集后，终端设备和服务器设备对采集的二维图像的数量和质量情况进一步沟通，可以进一步提高一次重建成功率。
在一种可能的实现方式中，所述图像补充采集方案包括缺陷提示信息，所述缺陷提示信息用于提示存在缺陷的原因。
在本申请实施例中，用户可以根据缺陷提示信息确定存在缺陷的原因，便于二维图像的补充采集。
在一种可能的实现方式中，所述向服务器设备发送三维模型重建指标信息，包括：响应于用户输入的三维模型重建指标输入信息和/或三维模型重建指标选择信息，向服务器设备发送三维模型重建指标信息，其中，所述三维模型重建指标信息与所述三维模型重建指标输入信息和/或三维模型重建指标选择信息相对应。
在本申请实施例中，根据用户输入的指标信息确定三维模型重建指标，满足用户对3D模型重建的个性化需求。
在一种可能的实现方式中，所述三维模型重建指标信息包括质量指标信息和/或物体指标信息，所述质量指标信息用于表征需要重建的三维模型的质量，所述物体指标信息用于表征需要重建的三维模型的尺寸。
在本申请实施例中，将质量指标信息和/或物体指标信息作为三维模型重建指标，满足用户对重建的三维模型的质量和/或尺寸的个性化需求。
在一种可能的实现方式中，所述质量指标信息包括需要重建的三维模型的平均差MSE和/或交并集交叉比例IoU；和/或，所述物体指标信息包括需要重建的三维模型的长宽高和/或需要重建的三维模型对应的球体的直径。
在一种可能的实现方式中，所述三维模型重建指标信息还包括性能指标信息，所述性能指标信息用于表征三维模型重建过程中用户期望耗费的资源。
在本申请实施例中，用户通过性能指标信息与服务器设备沟通期望耗费的资源，例如时间资源和/或计算资源，以便服务器设备在用户期望耗费的资源范围内执行3D模型重建操作，满足用户对耗费资源的个性化需求。
在一种可能的实现方式中，所述方法还包括：接收所述服务器设备发送的性能指标不可以满足三维模型重建要求指令，所述性能指标不可以满足三维模型重建要求指令用于表征用户期望耗费的资源不可以满足三维模型重建要求。
在本申请实施例中，当服务器设备判断用户期望耗费的资源不能满足三维模型重建要求时，将该信息发送至终端设备，以便用户调整三维模型重建指标信息，避免3D模型重建失败。
在一种可能的实现方式中，所述方法还包括：接收所述服务器设备发送的预估性能信息，所述预估性能信息包括三维模型重建过程中预估需要耗费的资源。
在本申请实施例中，服务器设备对三维模型重建过程中需要耗费的资源进行预估，例如时间资源和/或计算资源，并将预估的资源消耗信息发送至终端设备，以便用户判断是否可以满足对资源消耗的需求。
在一种可能的实现方式中，所述图像采集方案包括文本类图像采集引导信息和/或音视频图像采集引导信息。
在本申请实施例中，通过文本类图像采集引导信息和/或音视频图像采集引导信息进行二维图像采集的引导，易于实现，适用于较简单的二维图像采集场景。
第二方面，本申请实施例提供了一种终端设备，包括：一个或多个摄像头；一个 或多个处理器；存储器；以及一个或多个计算机程序，其中所述一个或多个计算机程序被存储在所述存储器中，所述一个或多个计算机程序包括指令，当所述指令被所述一个或多个处理器执行时，使得所述终端设备执行第一方面任意一项所述的方法。
第三方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质包括存储的程序，其中，在所述程序运行时控制所述计算机可读存储介质所在设备执行第一方面任意一项所述的方法。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其它的附图。
图1为本申请实施例提供的一种应用场景示意图；
图2为本申请实施例提供的一种电子设备的结构示意图；
图3为本申请实施例提供的一种3D模型重建场景示意图；
图4为本申请实施例提供的一种三维模型重建方法流程示意图；
图5A-5D为本申请实施例提供的一种三维模型重建指标配置场景示意图；
图6A-6C为本申请实施例提供的一种图像采集场景示意图；
图7A-7C为本申请实施例提供的一种图像采集引导场景示意图；
图8A-8E为本申请实施例提供的另一种图像采集引导场景示意图；
图9为本申请实施例提供的一种三维模型重建方法流程示意图；
图10为本申请实施例提供的一种图像补充采集方案示意图；
图11为本申请实施例提供的另一种图像补充采集方案示意图。
具体实施方式
为了更好的理解本申请的技术方案，下面结合附图对本申请实施例进行详细描述。
应当明确，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例，都属于本申请保护的范围。
在本申请实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
应当理解，本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，甲和/或乙，可以表示：单独存在甲，同时存在甲和乙，单独存在乙这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
在对本申请实施例进行具体介绍之前，首先对本申请所涉及的概念进行简单介绍。
本申请实施例涉及的重建对象为用户准备进行3D模型重建的三维物体，通过3D模型重建生成的3D模型为与所述重建对象相对应的3D模型。
本申请实施例涉及的照片为重建对象的照片，在一些实施例中，该照片也可能描述为图像、图片等。
本申请实施例涉及的硬件设备之间的信息交互，也可以理解为硬件设备上承载的软件工具之间的信息交互，例如，终端设备和服务器设备之间的信息交互可以理解为终端设备上的集成开发环境(Integrated development environment，IDE)和服务器设备上的云端计算环境(AR Cloud)之间的信息交互。其中，IDE用于提供程序开发环境的应用程序，包括代码编辑器、编译器、调试器和图形用户界面等工具，在3D模型重建中IDE用于上传照片、查看执行进度、预览3d模型等；AR Cloud是一个持续的点云地图与真实世界坐标的结合，通过对现实世界扫描建立实时更新的3D数字世界模型，在3D模型重建中AR Cloud用于执行3D模型重建计算过程等。例如，对IDE上传的图片执行photogrammetry pipeline计算，生成3D模型，photogrammetry pipeline是一种使用拍摄的照片创建3D模型的工具。
参见图1，为本申请实施例提供的一种应用场景示意图。如图1所示，本申请实施例涉及的电子设备包括终端设备101和服务器设备102，终端设备101和服务器设备102通过有线或无线通信网络互联，进行信息传输。该通信网络可以是局域网，也可以是通过中继(relay)设备转接的广域网。当该通信网络为局域网时，示例性的，该通信网络可以是wifi热点网络、wifi P2P网络、蓝牙网络、zigbee网络或近场通信(near field communication，NFC)网络等近距离通信网络。当该通信网络为广域网时，示例性的，该通信网络可以是第三代移动通信技术(3rd-generation wireless telephone technology，3G)网络、第四代移动通信技术(the 4th generation mobile communication technology，4G)网络、第五代移动通信技术(5th-generation mobile communication technology，5G)网络、未来演进的公共陆地移动网络(public land mobile network，PLMN)或因特网等。
终端设备101除了手机以外，还可以为平板电脑、个人计算机(personal computer，PC)、个人数字助理(personal digital assistant，PDA)、智能手表、上网本、可穿戴电子设备、增强现实技术(augmented reality，AR)设备、虚拟现实(virtual reality，VR)设备、车载设备、机器人、智能眼镜等。
在本申请实施例中，用户可以通过触发终端设备101，在终端设备101中输入一些指令，使终端设备101执行相应的操作，或者使终端设备101与服务器设备102进行相应的信息交互。本申请实施例对指令的触发形式不做限制，例如，可以为通过触摸屏、鼠标、键盘、按键等设备触发。
参见图2，为本申请实施例提供的一种电子设备的结构示意图。该电子设备200既可以为图1中的终端设备101，也可以为图1中的服务器设备102。
电子设备200可以包括处理器210，外部存储器接口220，内部存储器221，通用串行总线(universal serial bus，USB)接口230，充电管理模块240，电源管理模块241，电池242，天线1，天线2，移动通信模块250，无线通信模块260，音频模块270，扬声器270A，受话器270B，麦克风270C，耳机接口270D，传感器模块280，按键290，马达291，指示器292，摄像头293，显示屏294，以及用户标识模块(subscriber identification module，SIM)卡接口295等。其中传感器模块280可以包 括压力传感器280A，陀螺仪传感器280B，气压传感器280C，磁传感器280D，加速度传感器280E，距离传感器280F，接近光传感器280G，指纹传感器280H，温度传感器280J，触摸传感器280K，环境光传感器280L，骨传导传感器280M等。
可以理解的是，本发明实施例示意的结构并不构成对电子设备200的具体限定。在本申请另一些实施例中，电子设备200可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器210可以包括一个或多个处理单元，例如：处理器210可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器210中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器210中的存储器为高速缓冲存储器。该存储器可以保存处理器210刚用过或循环使用的指令或数据。如果处理器210需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器210的等待时间，因而提高了系统的效率。
在一些实施例中，处理器210可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。
I2C接口是一种双向同步串行总线，包括一根串行数据线(serial data line，SDA)和一根串行时钟线(derail clock line，SCL)。在一些实施例中，处理器210可以包含多组I2C总线。处理器210可以通过不同的I2C总线接口分别耦合触摸传感器280K，充电器，闪光灯，摄像头293等。例如：处理器210可以通过I2C接口耦合触摸传感器280K，使处理器210与触摸传感器280K通过I2C总线接口通信，实现电子设备200的触摸功能。
I2S接口可以用于音频通信。在一些实施例中，处理器210可以包含多组I2S总线。处理器210可以通过I2S总线与音频模块270耦合，实现处理器210与音频模块270之间的通信。在一些实施例中，音频模块270可以通过I2S接口向无线通信模块260传递音频信号，实现通过蓝牙耳机接听电话的功能。
PCM接口也可以用于音频通信，将模拟信号抽样，量化和编码。在一些实施例中，音频模块270与无线通信模块260可以通过PCM总线接口耦合。在一些实施例中，音频模块270也可以通过PCM接口向无线通信模块260传递音频信号，实现通过蓝 牙耳机接听电话的功能。所述I2S接口和所述PCM接口都可以用于音频通信。
UART接口是一种通用串行数据总线，用于异步通信。该总线可以为双向通信总线。它将要传输的数据在串行通信与并行通信之间转换。在一些实施例中，UART接口通常被用于连接处理器210与无线通信模块260。例如：处理器210通过UART接口与无线通信模块260中的蓝牙模块通信，实现蓝牙功能。在一些实施例中，音频模块270可以通过UART接口向无线通信模块260传递音频信号，实现通过蓝牙耳机播放音乐的功能。
MIPI接口可以被用于连接处理器210与显示屏294，摄像头293等外围器件。MIPI接口包括摄像头串行接口(camera serial interface，CSI)，显示屏串行接口(display serial interface，DSI)等。在一些实施例中，处理器210和摄像头293通过CSI接口通信，实现电子设备200的拍摄功能。处理器210和显示屏294通过DSI接口通信，实现电子设备200的显示功能。
GPIO接口可以通过软件配置。GPIO接口可以被配置为控制信号，也可被配置为数据信号。在一些实施例中，GPIO接口可以用于连接处理器210与摄像头293，显示屏294，无线通信模块260，音频模块270，传感器模块280等。GPIO接口还可以被配置为I2C接口，I2S接口，UART接口，MIPI接口等。
USB接口230是符合USB标准规范的接口，具体可以是Mini USB接口，Micro USB接口，USB Type C接口等。USB接口230可以用于连接充电器为电子设备200充电，也可以用于电子设备200与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他电子设备，例如AR设备等。
可以理解的是，本发明实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对电子设备200的结构限定。在本申请另一些实施例中，电子设备200也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。
充电管理模块240用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。在一些有线充电的实施例中，充电管理模块240可以通过USB接口230接收有线充电器的充电输入。在一些无线充电的实施例中，充电管理模块240可以通过电子设备200的无线充电线圈接收无线充电输入。充电管理模块240为电池242充电的同时，还可以通过电源管理模块241为电子设备供电。
电源管理模块241用于连接电池242，充电管理模块240与处理器210。电源管理模块241接收电池242和/或充电管理模块240的输入，为处理器210，内部存储器221，显示屏294，摄像头293，和无线通信模块260等供电。电源管理模块241还可以用于监测电池容量，电池循环次数，电池健康状态(漏电，阻抗)等参数。在其他一些实施例中，电源管理模块241也可以设置于处理器210中。在另一些实施例中，电源管理模块241和充电管理模块240也可以设置于同一个器件中。
电子设备200的无线通信功能可以通过天线1，天线2，移动通信模块250，无线通信模块260，调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。电子设备200中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开 关结合使用。
移动通信模块250可以提供应用在电子设备200上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块250可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。移动通信模块250可以由天线1接收电磁波，并对接收的电磁波进行滤波，放大等处理，传送至调制解调处理器进行解调。移动通信模块250还可以对经调制解调处理器调制后的信号放大，经天线1转为电磁波辐射出去。在一些实施例中，移动通信模块250的至少部分功能模块可以被设置于处理器210中。在一些实施例中，移动通信模块250的至少部分功能模块可以与处理器210的至少部分模块被设置在同一个器件中。
调制解调处理器可以包括调制器和解调器。其中，调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后，被传递给应用处理器。应用处理器通过音频设备(不限于扬声器270A，受话器270B等)输出声音信号，或通过显示屏294显示图像或视频。在一些实施例中，调制解调处理器可以是独立的器件。在另一些实施例中，调制解调处理器可以独立于处理器210，与移动通信模块250或其他功能模块设置在同一个器件中。
无线通信模块260可以提供应用在电子设备200上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。无线通信模块260可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块260经由天线2接收电磁波，将电磁波信号调频以及滤波处理，将处理后的信号发送到处理器210。无线通信模块260还可以从处理器210接收待发送的信号，对其进行调频，放大，经天线2转为电磁波辐射出去。
在一些实施例中，电子设备200的天线1和移动通信模块250耦合，天线2和无线通信模块260耦合，使得电子设备200可以通过无线通信技术与网络以及其他设备通信。所述无线通信技术可以包括全球移动通讯系统(global system for mobile communications，GSM)，通用分组无线服务(general packet radio service，GPRS)，码分多址接入(code division multiple access，CDMA)，宽带码分多址(wideband code division multiple access，WCDMA)，时分码分多址(time-division code division multiple access，TD-SCDMA)，长期演进(long term evolution，LTE)，BT，GNSS，WLAN，NFC，FM，和/或IR技术等。所述GNSS可以包括全球卫星定位系统(global positioning system，GPS)，全球导航卫星系统(global navigation satellite system，GLONASS)，北斗卫星导航系统(beidou navigation satellite system，BDS)，准天顶卫星系统(quasi-zenith satellite system，QZSS)和/或星基增强系统(satellite based augmentation systems，SBAS)。
电子设备200通过GPU，显示屏294，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏294和应用处理器。GPU用于执行数学和几何计 算，用于图形渲染。处理器210可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏294用于显示图像，视频等。显示屏294包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)，有机发光二极管(organic light-emitting diode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的，AMOLED)，柔性发光二极管(flex light-emitting diode，FLED)，Miniled，MicroLed，Micro-oLed，量子点发光二极管(quantum dot light emitting diodes，QLED)等。在一些实施例中，电子设备200可以包括1个或N个显示屏294，N为大于1的正整数。
电子设备200可以通过ISP，摄像头293，视频编解码器，GPU，显示屏294以及应用处理器等实现拍摄功能。
ISP用于处理摄像头293反馈的数据。例如，拍照时，打开快门，光线通过镜头被传递到摄像头感光元件上，光信号转换为电信号，摄像头感光元件将所述电信号传递给ISP处理，转化为肉眼可见的图像。ISP还可以对图像的噪点，亮度，肤色进行算法优化。ISP还可以对拍摄场景的曝光，色温等参数优化。在一些实施例中，ISP可以设置在摄像头293中。
摄像头293用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是电荷耦合器件(charge coupled device，CCD)或互补金属氧化物半导体(complementary metal-oxide-semiconductor，CMOS)光电晶体管。感光元件把光信号转换成电信号，之后将电信号传递给ISP转换成数字图像信号。ISP将数字图像信号输出到DSP加工处理。DSP将数字图像信号转换成标准的RGB，YUV等格式的图像信号。在一些实施例中，电子设备200可以包括1个或N个摄像头293，N为大于1的正整数。
作为举例，摄像头293可以为彩色摄像头，彩色摄像头用于采集目标物体的的彩色图像，包含当下流行的终端产品中通用的彩色摄像头。距离传感器280F用于获取目标物体的深度信，作为举例，距离传感器280F可以通过飞行时间(Time of Flight,TOF)技术和结构光技术实现。
其中，TOF技术是传感器(例如深度传感器模组)发出经调制的近红外光，遇物体后反射，传感器通过计算光线发射和反射时间差或相位差，来换算被拍摄景物的距离，以产生深度信息。此外，再结合彩色摄像头拍摄，就能将物体的三维轮廓以不同颜色代表不同距离的地形图方式呈现出来。
其中，结构光是—组由投影元件和摄像头组成的系统结构。用投影元件投射特定的光信息(如经过光栅衍射)到物体表面后及背景后，由摄像头采集。根据物体造成的光信号的变化(如光线粗细的变化与位移)来计算物体的位置和深度等信息；进而复原整个三维空间。
数字信号处理器用于处理数字信号，除了可以处理数字图像信号，还可以处理其他数字信号。例如，当电子设备200在频点选择时，数字信号处理器用于对频点能量进行傅里叶变换等。
视频编解码器用于对数字视频压缩或解压缩。电子设备200可以支持一种或多种 视频编解码器。这样，电子设备200可以播放或录制多种编码格式的视频，例如：动态图像专家组(moving picture experts group，MPEG)1，MPEG2，MPEG3，MPEG4等。
NPU为神经网络(neural-network，NN)计算处理器，通过借鉴生物神经网络结构，例如借鉴人脑神经元之间传递模式，对输入信息快速处理，还可以不断的自学习。通过NPU可以实现电子设备200的智能认知等应用，例如：图像识别，人脸识别，语音识别，文本理解等。
外部存储器接口220可以用于连接外部存储卡，例如Micro SD卡，实现扩展电子设备200的存储能力。外部存储卡通过外部存储器接口220与处理器210通信，实现数据存储功能。例如将音乐，视频等文件保存在外部存储卡中。
内部存储器221可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。内部存储器221可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储电子设备200使用过程中所创建的数据(比如音频数据，电话本等)等。此外，内部存储器221可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。处理器210通过运行存储在内部存储器221的指令，和/或存储在设置于处理器中的存储器的指令，执行电子设备200的各种功能应用以及数据处理。
电子设备200可以通过音频模块270，扬声器270A，受话器270B，麦克风270C，耳机接口270D，以及应用处理器等实现音频功能。例如音乐播放，录音等。
音频模块270用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块270还可以用于对音频信号编码和解码。在一些实施例中，音频模块270可以设置于处理器210中，或将音频模块270的部分功能模块设置于处理器210中。
扬声器270A，也称“喇叭”，用于将音频电信号转换为声音信号。电子设备200可以通过扬声器270A收听音乐，或收听免提通话。
受话器270B，也称“听筒”，用于将音频电信号转换成声音信号。当电子设备200接听电话或语音信息时，可以通过将受话器270B靠近人耳接听语音。
麦克风270C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。当拨打电话或发送语音信息时，用户可以通过人嘴靠近麦克风270C发声，将声音信号输入到麦克风270C。电子设备200可以设置至少一个麦克风270C。在另一些实施例中，电子设备200可以设置两个麦克风270C，除了采集声音信号，还可以实现降噪功能。在另一些实施例中，电子设备200还可以设置三个，四个或更多麦克风270C，实现采集声音信号，降噪，还可以识别声音来源，实现定向录音功能等。
耳机接口270D用于连接有线耳机。耳机接口270D可以是USB接口230，也可以是3.5mm的开放移动电子设备平台(open mobile terminal platform，OMTP)标准接口，美国蜂窝电信工业协会(cellular telecommunications industry association of the USA，CTIA)标准接口。
压力传感器280A用于感受压力信号，可以将压力信号转换成电信号。在一些实 施例中，压力传感器280A可以设置于显示屏294。压力传感器280A的种类很多，如电阻式压力传感器，电感式压力传感器，电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器280A，电极之间的电容改变。电子设备200根据电容的变化确定压力的强度。当有触摸操作作用于显示屏294，电子设备200根据压力传感器280A检测所述触摸操作强度。电子设备200也可以根据压力传感器280A的检测信号计算触摸的位置。在一些实施例中，作用于相同触摸位置，但不同触摸操作强度的触摸操作，可以对应不同的操作指令。例如：当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时，执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时，执行新建短消息的指令。
陀螺仪传感器280B可以用于确定电子设备200的运动姿态。在一些实施例中，可以通过陀螺仪传感器280B确定电子设备200围绕三个轴(即，x，y和z轴)的角速度。陀螺仪传感器280B可以用于拍摄防抖。示例性的，当按下快门，陀螺仪传感器280B检测电子设备200抖动的角度，根据角度计算出镜头模组需要补偿的距离，让镜头通过反向运动抵消电子设备200的抖动，实现防抖。陀螺仪传感器280B还可以用于导航，体感游戏场景。
气压传感器280C用于测量气压。在一些实施例中，电子设备200通过气压传感器280C测得的气压值计算海拔高度，辅助定位和导航。
磁传感器280D包括霍尔传感器。电子设备200可以利用磁传感器280D检测翻盖皮套的开合。在一些实施例中，当电子设备200是翻盖机时，电子设备200可以根据磁传感器280D检测翻盖的开合。进而根据检测到的皮套的开合状态或翻盖的开合状态，设置翻盖自动解锁等特性。
加速度传感器280E可检测电子设备200在各个方向上(一般为三轴)加速度的大小。当电子设备200静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。
距离传感器280F，用于测量距离。电子设备200可以通过红外或激光测量距离。在一些实施例中，拍摄场景，电子设备200可以利用距离传感器280F测距以实现快速对焦。
接近光传感器280G可以包括例如发光二极管(LED)和光检测器，例如光电二极管。发光二极管可以是红外发光二极管。电子设备200通过发光二极管向外发射红外光。电子设备200使用光电二极管检测来自附近物体的红外反射光。当检测到充分的反射光时，可以确定电子设备200附近有物体。当检测到不充分的反射光时，电子设备200可以确定电子设备200附近没有物体。电子设备200可以利用接近光传感器280G检测用户手持电子设备200贴近耳朵通话，以便自动熄灭屏幕达到省电的目的。接近光传感器280G也可用于皮套模式，口袋模式自动解锁与锁屏。
环境光传感器280L用于感知环境光亮度。电子设备200可以根据感知的环境光亮度自适应调节显示屏294亮度。环境光传感器280L也可用于拍照时自动调节白平衡。环境光传感器280L还可以与接近光传感器280G配合，检测电子设备200是否在口袋里，以防误触。
指纹传感器280H用于采集指纹。电子设备200可以利用采集的指纹特性实现指纹解锁，访问应用锁，指纹拍照，指纹接听来电等。
温度传感器280J用于检测温度。在一些实施例中，电子设备200利用温度传感器280J检测的温度，执行温度处理策略。例如，当温度传感器280J上报的温度超过阈值，电子设备200执行降低位于温度传感器280J附近的处理器的性能，以便降低功耗实施热保护。在另一些实施例中，当温度低于另一阈值时，电子设备200对电池242加热，以避免低温导致电子设备200异常关机。在其他一些实施例中，当温度低于又一阈值时，电子设备200对电池242的输出电压执行升压，以避免低温导致的异常关机。
触摸传感器280K，也称“触控器件”。触摸传感器280K可以设置于显示屏294，由触摸传感器280K与显示屏294组成触摸屏，也称“触控屏”。触摸传感器280K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏294提供与触摸操作相关的视觉输出。在另一些实施例中，触摸传感器280K也可以设置于电子设备200的表面，与显示屏294所处的位置不同。
骨传导传感器280M可以获取振动信号。在一些实施例中，骨传导传感器280M可以获取人体声部振动骨块的振动信号。骨传导传感器280M也可以接触人体脉搏，接收血压跳动信号。在一些实施例中，骨传导传感器280M也可以设置于耳机中，结合成骨传导耳机。音频模块270可以基于所述骨传导传感器280M获取的声部振动骨块的振动信号，解析出语音信号，实现语音功能。应用处理器可以基于所述骨传导传感器280M获取的血压跳动信号解析心率信息，实现心率检测功能。
按键290包括开机键，音量键等。按键290可以是机械按键。也可以是触摸式按键。电子设备200可以接收按键输入，产生与电子设备200的用户设置以及功能控制有关的键信号输入。
马达291可以产生振动提示。马达291可以用于来电振动提示，也可以用于触摸振动反馈。例如，作用于不同应用(例如拍照，音频播放等)的触摸操作，可以对应不同的振动反馈效果。作用于显示屏294不同区域的触摸操作，马达291也可对应不同的振动反馈效果。不同的应用场景(例如：时间提醒，接收信息，闹钟，游戏等)也可以对应不同的振动反馈效果。触摸振动反馈效果还可以支持自定义。
指示器292可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。
SIM卡接口295用于连接SIM卡。SIM卡可以通过插入SIM卡接口295，或从SIM卡接口295拔出，实现和电子设备200的接触和分离。电子设备200可以支持1个或N个SIM卡接口，N为大于1的正整数。SIM卡接口295可以支持Nano SIM卡，Micro SIM卡，SIM卡等。同一个SIM卡接口295可以同时插入多张卡。所述多张卡的类型可以相同，也可以不同。SIM卡接口295也可以兼容不同类型的SIM卡。SIM卡接口295也可以兼容外部存储卡。电子设备200通过SIM卡和网络交互，实现通话以及数据通信等功能。在一些实施例中，电子设备200采用eSIM，即：嵌入式SIM卡。eSIM卡可以嵌在电子设备200中，不能和电子设备200分离。
在一种可能的实现方式中，3D模型重建工具包括IDE和AR Cloud两部分。其中，用户可以通过IDE上传照片、查看执行进度、预览3D模型等；AR Cloud用于执行3D模型重建计算过程，生成3D模型。
但是，AR Cloud执行3D模型重建的过程非常耗时，例如，用户在将照片上传至AR Cloud之后，可能需要等待5个小时以上，才能查看AR Cloud的重建结果。可理解，用户上传的照片的质量将影响重建的3D模型的质量，如果用户上传的照片不符合要求，例如上传的照片不全、照片的清晰度不够、照片的角度或距离不符合要求等，将会导致重建的3D模型精细度不够、模型有缺失、变形等。此时，用户只能重新拍摄、上传照片至AR Cloud，AR Cloud重新执行3D模型重建的操作，用户需要再次等待3D模型重建过程，浪费用户时间，用户体验较差。
针对该问题，本申请实施例提供了一种3D模型重建方案，在执行3D模型重建之前，用户提交对3D模型的质量预期，根据用户对3D模型的质量预期，生成图像采集方案，指导用户进行重建对象的照片采集。可理解，相对于用户自行采集的照片，在图像采集方案的指导下采集的照片质量更高，提高一次重建成功率。另外，还可以根据用户采集的照片预先对3D模型重建的效果进行估算，只有3D模型重建的效果符合用户的质量预期后，才执行3D模型重建过程，进一步提高一次重建成功率。以下结合附图进行详细说明。
参见图3，为本申请实施例提供的一种3D模型重建场景示意图。在图3中，以动物模型玩具为例，对本申请实施例提供的3D模型重建场景进行简单介绍。
图3A为重建对象，该重建对象为用户拥有的一个动物模型玩具，用户希望对该动物模型玩具进行3D模型重建，换句话讲，用户希望重建的3D模型为该动物模型玩具对应的3D模型。在执行3D模型重建之前，用户提交对3D模型的质量预期，例如，用户希望构建一个1000面、平均差(Mean Square Error，MSE)在2mm以内的3D模型，3D模型的直径在10cm以内。其中，面数用于描述组成3D模型的多边形的数量，面数越多模型越平滑，细节越丰富；MSE用于描述建模后3D模型的点和实际物体对应的点之间距离的平均差；直径用于描述3D模型对应的球体的直径，即利用3D模型对应的球体的大小对3D模型的尺寸进行衡量，当然也可以利用3D模型的长宽高对3D模型的尺寸进行衡量。
图3B为AR Cloud根据用户的质量预期生成的图像采集方案，用户将3D模型的质量预期提交至AR Cloud后，AR Cloud根据该质量预期生成对应的图像采集方案。在图3B中，图像采集方案要求用户在距离动物模型玩具60cm的距离，从8个角度，在高度上分3个层次，拍摄24张照片。
图3C为用户根据图像采集方案采集的动物模型玩具的24张照片，在高度上分3个层次，每层8张照片。其中，对于不同层，从不同的高度视角进行照片采集，例如，图3C中的第1层照片为动物模型玩具的仰视图，第2层照片为动物模型玩具的平视图，第3层照片为动物模型玩具的俯视图。对于同一层，从8个角度采集动物模型玩具一周的照片，例如，每隔45°的采集一张照片，分别从0°、45°、90°、135°、180°、225°、270°、315°位置采集8张照片。可理解，此处的图像采集方案仅是示例性说明，AR Cloud会根据不同的质量预期生成不同的图像采集方案，例如，除了 从高度上分层次采集照片外，还可能会要求用户从深度上分层次采集照片等。
图3D为照片集合的摘要信息，用户完成照片采集后，根据采集的照片集合，生成照片集合的摘要信息，并将该摘要信息发送至AR Cloud，AR Cloud根据该摘要信息验证用户采集的照片集合是否满足3D模型重建需求。例如，该摘要信息可以包括照片的数量，每张照片的采集角度，照片的低分辨率版本等。AR Cloud接收到摘要信息后，根据该摘要信息判断每张照片的拍摄质量，例如照片的分辨率、光照、饱和度、清晰度、物体在照片中的比例、拍摄的角度、背景色等，进而判断用户采集的照片集合是否可以满足3D模型重建需求。若判断可以满足3D模型重建需求，则执行3D模型重建操作，否则，通知用户对照片进行补充后，重新判断用户采集的照片是否满足3D模型重建需求。
图3E为AR Cloud重建的3D模型，AR Cloud完成3D模型重建后，将重建的3D模型发送至终端设备，用户获得该动物模型玩具的3D模型，完成3D模型重建。
本申请实施例在3D模型重建过程中增加重建沟通环节，对3D模型重建要求和图像采集方案进行沟通，避免采集的二维图像不符合3D模型重建要求，而引起的3D模型重建失败的问题，提高一次重建成功率。
参见图4，为本申请实施例提供的一种三维模型重建方法流程示意图。该方法可应用于图1所示的设备，如图4所示，其主要包括以下步骤。
步骤S401：终端设备向服务器设备发送三维模型重建指标信息。
所述三维模型重建指标信息用于表征三维模型重建要求，在一种可选实施例中，所述三维模型重建指标信息包括3D模型的质量指标信息和/或物体指标信息。其中，所述质量指标信息用于表征需要重建的3D模型的质量，所述物体指标信息用于表征需要重建的3D模型的尺寸。
具体地，所述3D模型的质量包括3D模型的准确性、完整性、一致性等指标，可以通过平均差(Mean Square Error，MSE)和/或交并集交叉比例(Intersection over Union，IoU)进行衡量。MSE用于描述建模后3D模型的点和实际物体对应的点之间距离的平均差；IoU用于描述是建模后3D模型和实际物体的交集和并集的比值。需要指出的是，质量指标信息和建模后3D模型的面数相关，质量指标越高，建模后3D模型的面数越多，其中，面数是指组成3D模型的多边形的数量，面数越多模型越平滑，细节越丰富。可理解，质量指标越高，需要用户采集的照片的数量越多、质量越高，3D模型重建需要花费的时间越长，消耗的计算资源越多，该计算资源包括内存、处理器资源等。
一方面，3D模型的尺寸可以通过3D模型的长宽高表示；另一方面，3D模型的尺寸可以通过3D模型对应的球体的直径表示。可理解，3D模型的尺寸越大，需要用户采集的照片的数量越多、质量越高，由二维图像生成3D模型的过程需要花费的时间越长，消耗的计算资源越多。
参见图5A-5D，为本申请实施例提供的一种三维模型重建指标配置场景示意图。终端设备在向服务器设备发送三维模型重建指标信息之前，终端设备展示三维模型重建指标配置窗口，用户可以在该窗口内部相应的位置输入期望的质量指标和/或物体指标，对三维模型重建指标进行配置，用户在该窗口内输入的信息即三维模型重建指标 输入信息。例如，用户在该窗口的输入区域内输入：“IoU，99％；物体尺寸，8cm”。需要指出的是，在图5A所示的实施例中，采用IoU描述质量指标，当然，本领域技术人员也可以根据实际需要采用MSE描述质量指标，或者采用MSE和IoU描述质量指标，本申请实施例对此不作限制。
为了便于用户操作，质量指标还可以按照区间划分为高、中、低三个选项供用户选择。例如，用户在质量指标处输入：“质量指标，高”，而无需输入质量指标的具体数值。
另外，所述三维模型重建指标信息中还可能包含性能指标信息，所述性能指标信息用于表征3D模型重建过程的用户期望的耗费的资源，所述用户期望耗费的资源包括用户期望耗费的时间资源和/或计算资源。例如，希望耗费的时长和/或预计使用的计算资源，该计算资源包括内存、处理器资源等。例如，用户希望在6个小时内完成3D模型重建，占用系统1.8G内存，单核处理器。该性能指标信息为3D模型重建过程中，用户对资源消耗的期望值。
如图5B所示，在图5B的三维模型重建指标配置窗口中包含质量指标、物体指标和性能指标，用户可以在该窗口内部相应的位置输入期望的质量指标、物体指标和/或性能指标，对三维模型重建指标进行配置。
可理解，计算资源配置越高，3D模型重建速度越快，耗费的时长越短。但是，在实际应用场景中，用户在AR Cloud中占用不同的计算资源可能对应不同的资费，用户可以根据其预期的花费选择对应的计算资源。
如图5C所示，终端设备接收到用户输入的资费套餐展示指令后，在显示屏中展示资费套餐窗口。资费套餐选择窗口中包含不同资费套餐下对应的计算资源，用户可以根据预期的花费选择对应的计算资源。例如，用户选择20元的资费套餐，在3D模型重建中，将获得2G内存和双核处理器的计算资源。
另外，为了便于用户操作，可以在三维模型重建指标配置窗口中展示一系列预设的三维模型重建指标，用户根据需要，进行三维模型重建指标的选择，即在三维模型重建指标配置窗口中输入三维模型重建指标选择信息，完成指标配置。例如，在图5D中，用户通过点击窗口中相应的位置，选择“质量指标，中；物体尺寸，10-50cm；耗时，6小时；内存，1.6G；处理器，双核”的配置信息，终端设备将该配置信息发送至AR Cloud。
需要指出的是，图5A-5D仅是一种示例性说明，本领域技术人员可以根据实际需要对三维模型重建指标信息的配置进行相应调整。例如，在性能指标中，除了处理器的核数外，还可以配置处理器的主频值；不同资费套餐中对应的计算资源也可以根据实际需要进行相应调整。
步骤S402：服务器设备根据所述三维模型重建指标信息确定图像采集方案。
在本申请实施例中，服务器设备在接收到三维模型重建指标信息后，确定可以满足该三维模型重建指标要求的图像采集方案。
照片的采集是整个3D模型重建过程中非常重要的一步，重建结果的好坏往往与采集的照片有很大的关系。可理解，为了达到不同的质量指标和/或物体指标，所需要的照片的数量和质量也不尽相同。该图像采集方案可以包括照片的数量、角度、距离、 分辨率、光照条件、背景要求等。以下进行详细说明。
通常情况下，重建对象的每一部分应该从多个不同的视角进行拍摄。换句话讲，环绕重建对象拍摄的照片应该保证一定的重叠区域，且不同的质量指标和/或物体指标对该重叠区域的要求不同。由于照片数量和角度将影响重叠区域的大小，因此，不同的质量指标和/或物体指标对照片的数量和拍摄角度要求不同。
参见图6A-6C，为本申请实施例提供的一种图像采集场景示意图。在图6A中示出了图像采集设备601和重建对象602，在图6A左侧的图像采集场景中，图像采集设备601从8个视角环绕重建对象602进行拍摄，拍摄8张照片，其中，在两个相邻的拍摄视角处，重叠的图像采集区域形成重叠区域。也就是说，在两个相邻的拍摄视角处采集的两张照片中，存在重叠部分。
在图6A右侧的图像采集场景中，图像采集设备601从16个视角环绕重建对象602进行拍摄，拍摄16张照片。
可理解，按照图6A左侧的图像采集方案采集的照片重叠区域占比较小；按照图6A右侧的图像采集方案采集的照片重叠区域占比较大。因此，当3D模型重建的质量指标和/或物体指标要求较高时，应当拍摄更多的照片，且合理的控制不同照片之间的角度，以获得较高占比的重叠区域。
需要指出的是，本申请实施例涉及的角度，除了包括同一水平面内不同拍摄视角之间的相对角度外，还包括不同高度上的拍摄角度。尤其是对于具备一定高度的重建对象，需要从不同高度上分层次进行图像采集。
在图6B中，图像采集设备601从高度方向上分3个层次进行图像采集，分别为第1层，第2层和第3层。对于其中每一层的拍摄视角和拍摄数量，可以参见图6A中的描述，本申请实施例在此不再赘述。
在图6C中，图像采集设备601相对重建对象602由远及近、从不同的距离分3个层次进行图像采集，分别为第1层，第2层和第3层。该方式可以最大程度地还原照片重建后的纹理信息，因此，对于质量指标要求较高的重建对象，应该由远及近、从不同的距离上分层拍摄。
可理解，重建的3D模型的质量与采集的照片的分辨率直接相关，因此，质量指标越高，相应的需要采集的照片的分辨率越高。具体实现中，可以通过不同分辨率的摄像头采集不同分辨率的照片。例如，图像采集设备包括500M分辨率摄像头和1000M分辨率摄像头，当质量指标较高时，采用1000M分辨率摄像头进行图像采集；当质量指标较低时，采用500M分辨率摄像头进行图像采集。
对于光照条件，由于直射光或不断变化的光照将会增加曝光过度或曝光不足的风险，因此稳定的环境光源将会提高采集的照片的质量。当3D模型重建的质量指标和/或物体指标要求较高时，应该确保光照条件为稳定的环境光源。
对于背景，不同照片的背景应该保持统一，且不能过于杂乱，以免影响3D模型重建。需要指出的是，对于纹理比较单一的重建对象，需要在拍摄范围内增加一个背景图案，以使得从不同角度拍摄的照片的相对位置不同。
具体实现中，在获得终端设备发送的三维模型重建指标信息后，服务器设备可以通过算法预估，生成图像采集方案。具体地，可以将三维模型重建指标信息作为预设 的算法模型的输入参数，三维模型重建指标信息输入算法模型后，输出图像采集方案。本申请实施例对该算法模型不作具体限定。
在另一种可能的实现方式中，可以通过查找预设的图像采集方案对照表，确定图像采集方案。
参见表1，为本申请实施例提供的一种图像采集方案对照表。该图像采集方案对照表可以根据经验预先配置，包括质量指标、物体指标、图像采集方案，以及其对应关系。
表1：
质量指标 物体指标(尺寸) 图像采集方案
高 小于10cm 机位C
高 10cm-50cm 机位D
高 大于50cm 机位E
中 小于10cm 机位B
中 10cm-50cm 机位C
中 大于50cm 机位D
低 小于10cm 机位A
低 10cm-50cm 机位B
低 大于50cm 机位C
在表1中，将质量指标按照区间划分为高中低三类，例如，终端设备发送的质量指标信息中，若IoU>98％，表示质量指标“高”；若95％≤IoU≤98％，表示质量指标“中”；若90％≤IoU＜95％，表示质量指标“低”。
在本申请实施例中，物体的尺寸采用3D模型对应的球体的大小进行描述，按照对应的球体的直径划分为三个区间，小于10cm，10-50cm，大于50cm。
根据不同的质量指标和物体指标，系统预先定义了A,B,C,D,E五种机位，所述机为即图像采集方案，不同的机位分别表示不同的拍照要求。例如：
机位A表示使用200M分辨率摄像头，环绕重建对象从4个位置拍摄，要求光照强度在200流明以上。其中，流明为描述光通量的物理单位。
机位B表示使用500M分辨率摄像头，环绕重建对象从4个位置拍摄，要求光照强度300流明以上。
机位C表示使用1000M以上分辨率摄像头，环绕重建对象从4个位置拍摄，要求重建对象占据画面60％以上，光照强度在500流明。其中，通过重建对象在照片画面中的占比，可以反映出图像采集设备与重建对象之间的距离。
机位D表示使用1000M以上分辨率摄像头，环绕重建对象从16个位置拍摄，要求物体占据画面60％以上，光照强度在500流明。
机位E表示使用1000M以上分辨率摄像头，环绕重建对象从24个位置拍摄，要 求物体占据画面60％以上，光照强度在500流明。
另外，根据质量指标信息和物体指标信息，AR Cloud还可以生成预估性能信息。所述预估性能信息用于表征三维模型重建过程中预估需要耗费的资源，所述预估需要耗费的资源包括预估需要耗费的时间资源和/或计算资源。例如，计算资源可以包括内存和/或处理器资源等。当然，该预估性能信息也可以同时预先配置在图像采集方案对照表中，通过查表确定质量指标信息和物体指标信息对应的预估性能信息，如表2所示。
表2：
Figure PCTCN2021138868-appb-000001
需要指出的是，三维模型重建指标信息中的性能指标信息为用户期望的性能信息，AR Cloud生成的预估性能信息为AR Cloud根据质量指标和物体指标预估的性能信息。当终端设备发送的三维模型重建指标信息中包含用户期望的性能信息时，AR Cloud通过比较预估的性能信息和用户期望的性能信息，判断用户期望的性能信息是否可以满足3D模型重建需求，若可以满足3D模型重建需求，则根据用户期望的性能信息分配计算资源；若不可以满足3D模型重建需求，则根据预估性能信息分配计算资源。实际应用场景中，当用户期望的性能信息不能满足3D模型重建需求时，AR Cloud还可以将其预估的性能信息发送至终端设备，供用户确认或选择。
另外，对于同样的质量指标和物体指标，性能指标中计算资源越多，3D模型重建过程中耗费的时长越短。当用户期望的性能指标信息中仅包含时间资源时，AR Cloud可以根据用户期望的时间资源分配相对应的计算资源；当用户期望的性能指标信息中仅包含计算资源时，AR Cloud可以根据用户期望的计算资源预估时间资源，即预估需要耗费的时长，并将该预估的时长发送至终端设备供用户参考。
步骤S403：服务器设备向终端设备发送所述图像采集方案。
在本申请实施例中，服务器设备生成图像采集方案后，将该图像采集方案发送至终端设备，以便终端设备根据该图像采集方案进行图像采集。
步骤S404：终端设备根据所述图像采集方案，采集重建对象的二维图像。
具体实现中，该图像采集方案可以为具体的图像采集引导信息，例如文本类图像采集引导信息，用户根据该文本类图像采集引导信息的指示进行照片拍摄。该过程为人工配置过程，例如，用户根据图像采集方案的说明，自行进行背景设置、光照条件设置，手持图像采集设备围绕重建对象进行拍摄，获得重建对象的二维图像。
除了文本类图像采集引导信息外，该图像采集方案还可以为音视频图像采集引导信息，例如视频教程，所述视频教程可以以图文声音的方式指导用户拍摄。
为了便于用户操作，该图像采集方案还可以为终端设备可读文件，通过读取图像采集方案，终端设备上生成图像采集引导程序，通过引导程序引导用户进行拍摄，以提高图像采集的便捷性及准确性。可理解，当通过引导程序引导用户进行拍摄时，引导程序同时还需要进行光照检测和背景检测，以判断光照条件或背景是否符合图像采集方案的要求。
在一种可选实施例中，图像采集引导程序包括移动方向指引信息，所述移动方向指引信息用于提示向目标位置移动，提高人机交互的友好性。以下结合附图进行详细说明。
参见图7A-7C，为本申请实施例提供的一种图像采集引导场景示意图。在图7A-7C示出的显示界面内设有图像采集窗口，该图像采集窗口内包括图像采集框(虚线框)701和引导箭头702，该引导箭头702即移动方向指引信息。在进行图像采集时，重建对象保持不动，终端设备环绕重建对象360°，从多个不同的视角进行拍摄。图像采集框701实时显示摄像头对应的影像信息，图像采集框701四周的引导箭头702用于指引终端设备的移动方向。
例如，终端设备需要环绕重建对象360°采集8张照片，平均每隔45°采集一张照片。终端设备可以从任意角度拍摄1张照片，并以该位置作为起点，向右转动45°后，拍摄第2张照片。其中，在终端设备移动时，终端设备中的陀螺仪和加速度传感器可以实时检测终端设备转动的角度和/或移动的距离，进而通过图像采集框701四周的引导箭头702给予指引。例如，在图7B中，终端设备采集完第1张照片后，图像采集框701右侧的箭头高亮，指引用户向右侧转动终端设备，当终端设备检测用户转动到第2个图像采集点时，图像采集框701右侧的箭头恢复正常，终端设备在该位置采集第2张照片，如图7C所示。依次类推，终端设备完成所有照片的采集。
在本申请实施例中，通过移动方向指引信息指引用户将终端设备移动至目标位置，便于用户操作，提高人机交互的友好性。
可理解，上述目标位置为图像采集方案中未完成二维图像采集的位置，即该移动方向指引信息应当指引终端设备向未完成图像采集的位置移动。其中，当存在多个未完成二维图像采集的位置时，可以指引终端设备向任意一个未完成图像采集的位置移动。
但是，为了提高二维图像的采集效率，且避免二维图像的遗漏，在一种可选实施例中，图像采集引导程序还包括图像采集顺序，引导用户按照图像采集顺序完成二维图像的采集。具体地，在完成第一采集位置的第一二维图像采集后，输出第一采集位置至第二采集位置的移动方向指引信息，所述第一采集位置至第二采集位置的移动方 向指引信息用于提示向第二采集位置移动。采用本方案，便于用户按照预设的图像采集顺序，依次完成所有二维图像的采集，提高二维图像的采集效率，且避免二维图像的遗漏。需要指出的是，本申请实施例对移动方向指引信息的具体形式不作限制。例如，除了上述实施例中的引导箭头外，还可以为语音引导信息，或者显示界面中其它类型的指示信息。例如，图像采集引导程序包括三维图像采集场景，在该三维图像采集场景中对需要进行二维图像采集的位置进行标记。可理解，该标记的位置即目标位置，用户可以通过该标记的位置确定终端设备的移动方向，该标记的位置即移动方向指引信息。以下结合图8A-8E进行详细说明，在图8A-8E中，通过图像采集定位框对需要进行二维图像采集的位置进行标记。
参见图8A-8E，为本申请实施例提供的另一种图像采集引导场景示意图。在图8A-8E中示出了图像采集框(虚线框)801、图像采集定位框(实线框)802和引导箭头803。在进行图像采集时，重建对象保持不动，终端设备环绕重建对象360°、从多个不同的视角进行拍摄。其中，当终端设备移动时，终端设备中的陀螺仪传感器和加速度传感器可以实时检测终端设备转动的角度和/或移动的距离，进而使图像采集定位框802在屏幕中转动相应的角度和/或移动相应的距离。需要指出的是，图像采集定位框802在显示界面内的移动方向与终端设备的移动方向相反。例如，当终端设备向右移动时，图像采集定位框802在显示界面内向左移动。在本申请实施例中，引导箭头803用于指示图像采集定位框802在显示界面内的移动方向，当然也可以不包含引导箭头803，本申请实施例对此不作限制。
另外，由于终端设备移动时，图像采集框801在屏幕中的位置不变，因此，用户可以通过图像采集框801和图像采集定位框802的相对位置，判断终端设备的移动方向，以及判断终端设备是否移动到相应的位置。当判断终端设备移动到相应的位置时，控制终端设备拍摄，以获得该图像采集视角处的照片。其中，拍摄动作可以由终端设备自动触发，也可以由用户触发，本申请实施例对此不作限制。
通常情况下，引导程序中包含多个图像采集定位框802，每个图像采集定位框802代表一个拍摄视角，引导程序根据图像采集方案预先设置每个图像采集定位框802的位置。例如，在图8A-8E所示的实施例中，需要环绕重建对象一周均匀地采集8张照片，也就是说，环绕重建对象每隔45°采集一张照片。相应的，在引导程序中包括8个图像采集定位框802，该8个图像采集定位框802环绕一周，相邻的图像采集定位框802之间间隔45°。
在一种可选实施例中，为了进一步提高人机交互界面的友好性，在每个图像采集定位框802上设有编号，例如，在图8A中示出了图像采集定位框①，图像采集定位框②和图像采集定位框⑧。当终端设备移动到图8A所示的位置时，图像采集定位框①与图像采集框801相匹配，此时触发终端设备采集第1张照片。完成第1张照片的采集后，终端设备向右转动，相应的，图像采集定位框802在屏幕内向左转动(如图8B中的箭头所示)，移动至图8B所示的位置，此时，图像采集定位框②还未移动至图像采集框801相匹配的位置。终端设备继续向右移动，图像采集定位框②在屏幕内继续向左移动，移动至图8C所示的位置，此时图像采集定位框②与图像采集框801相匹配，触发终端设备采集第2张照片。依次类推，用户根据引导程序中图像采集定 位框802的指示，完成所有照片的采集。
另外，为了提高人机交互的友好性，终端设备可以自行判断是否移动至目标位置。当终端设备判断移动至目标位置时，输出到达目标位置提示信息，避免用户在未到达目标位置或超过目标位置时触发终端设备的图像采集动作，影响采集的二维图像的质量。其中，该到达目标位置提示信息可以为语音提示信息、显示界面中的指示信息或指示灯等，本申请实施例对此不作具体限制。具体实现中，终端设备可以通过陀螺仪传感器和加速度传感器实时检测终端设备转动的角度和/或移动的距离，进而判断是否移动至目标位置。
在一种可选实施例中，为了进一步提高人机交互界面的友好性，可以在显示界面中实时展示已经完成采集的二维图像的预览图像，以便用户实时了解二维图像的采集进度。另外，用户还可以根据该预览图像进行核查，避免二维图像的遗漏。
例如，在图8D中，在完成图像采集定位框①位置处的照片采集后，在图像采集定位框①位置展示采集的照片的预览图像，该方式可以便于用户了解图像采集进度。
在一种可选实施例中，为了进一步提高人机交互界面的友好性，将终端设备的显示屏分为图像预览窗口和图像采集窗口，如图8E所示。为了便于说明，将图像预览窗口内的定位框称为图像预览定位框804。其中，在图像预览窗口内展示整个图像采集方案示意图，包括图像预览定位框804的数量以及图像预览定位框804的位置。另外，在图像预览窗口内还可以展示当前的图像采集进度。具体地，在完成采集的图像预览定位框804位置，展示采集的照片的预览图像。如图8E所示，在完成图像采集定位框①和图像采集定位框②位置处的照片采集后，在图像预览窗口内、图像预览定位框①和图像预览定位框②位置展示采集的照片的预览图像。需要指出的是，图像预览窗口内可以展示固定的画面(图像预览窗口内的图像预览定位框804不随着终端设备的移动或转动而对应的移动或转动)，也可以展示运动的画面(图像预览窗口内的图像预览定位框804随着终端设备的移动或转动而对应的移动或转动)，本申请实施例对此不作限制。另外，图像采集窗口内的图像采集方式与图8A-8D所示实施例描述的图像采集方式相似，在此不再赘述。
在上述实施例中，图像采集引导程序引导用户手动完成二维图像的采集。在一种可选实施例中，通过所述图像采集引导程序控制机械臂带动所述终端设备移动至目标位置，采集所述重建对象的二维图像。通过机械臂进行二维图像的采集可以进行更加精准的控制，二维图像的采集精度更高。
本申请实施例在3D模型重建过程中增加重建沟通环节，对3D模型重建要求和图像采集方案进行沟通，避免采集的二维图像不符合3D模型重建要求，而引起的3D模型重建失败的问题，提高一次重建成功率。参见图9，为本申请实施例提供的另一种三维模型重建方法流程示意图。如图9所示，该方法在图4所示实施例的步骤S404之后，还包括以下步骤。
步骤S901：终端设备对采集的所述二维图像进行预处理，获得所述二维图像的摘要信息。
在本申请实施例中，终端设备在完成照片采集后，对采集的照片进行预处理，生成采集的照片的摘要信息，所述摘要信息用于判断采集的照片是否满足图像采集方案 中对照片的要求，即是否满足三维模型重建要求。具体地，所述摘要信息包括照片的数量，每张照片的采集角度，照片的低分辨率版本等。
步骤S902：终端设备向服务器设备发送所述二维图像的摘要信息。
终端设备在获得所述二维图像的摘要信息后，将所述摘要信息发送至服务器设备，以便服务器设备根据所述摘要信息判断终端设备采集的照片是否可以满足3D模型重建要求。
步骤S903：服务器设备根据所述二维图像的摘要信息判断采集的所述二维图像集合是否满足三维模型重建要求。
具体地，服务器设备可以根据所述摘要信息判断终端设备采集的照片的数量，以及每张照片的质量是否符合要求。照片的质量的评价指标包括分辨率、光照、饱和度、清晰度、重建对象在照片中的比例、拍摄的角度、背景色等。
步骤S904：若采集的所述二维图像满足三维模型重建要求，则向终端设备发送二维图像满足条件指令。
在本申请实施例中，若服务器设备判断终端设备采集的二维图像满足三维模型重建要求，说明可以在相应的时间内完成符合质量指标和物体指标要求的三维模型重建，则向终端设备发送二维图像满足条件指令。
服务器设备接收到二维图像满足条件指令后，向服务器设备发送采集的二维图像，以便服务器设备执行3D模型重建操作。
步骤S905：若采集的所述二维图像不满足三维模型重建要求，则生成图像补充采集方案。
在本申请实施例中，若服务器设备判断终端设备采集的二维图像不满足三维模型重建要求，说明使用采集的二维图像不能在相应的时间内完成符合质量指标和物体指标要求的三维模型重建，服务器设备则根据所述摘要信息生成图像补充采集方案。
例如，在图像采集方案中要求终端设备采集8张照片，而服务器设备根据摘要信息确定终端设备仅采集了7张照片，因此，可以确定终端设备采集的照片的数量不符合要求，需要对照片进行补充采集。
步骤S906：服务器设备向终端设备发送图像补充采集方案。
服务器设备在生成图像补充采集方案后，将该图像补充采集方案发送至终端设备，以便终端设备根据所述图像补充采集方案补充采集二维图像。
具体实现中，所述图像补充采集方案可以为图像补充采集引导程序、文本类图像补充采集引导信息和/或音视频图像补充采集引导信息，例如，拍摄教程，所述拍摄教程可以以图文声音的方式指导用户拍摄。
在一种可能的实现方式中，所述图像补充采集方案包括缺陷提示信息，该缺陷提示信息用于提示用户存在缺陷的原因，便于用户补充采集二维图像。
参见图10，为本申请实施例提供的一种图像补充采集方案示意图。在图10所示的实施例中，图像采集方案要求采集的照片中重建对象的占比应当大于60％。但是用户采集的二维图像中，存在一张“重建对象的占比小于60％”的二维图像，因此，判定该二维图像不满足要求，生成图像补充采集方案。服务器设备将该图像补充采集方案发送至终端设备。该图像补充采集方案包括不满足要求的二维图像，以及该二维图 像不满足要求的原因“照片中重建对象占比小于60％”，如图10所示。用户根据上述信息，可以很容易的确定需要补充采集的二维图像，以及补充采集二维图像时的注意事项，以确保补充采集的二维图像符合图像补充采集方案的要求。
参见图11，为本申请实施例提供的另一种图像补充采集方案示意图。其中，在图11中示出了一张二维图像，该二维图像曝光过度，不满足3D模型重建要求，生成图像补充采集方案。服务器设备将该图像补充采集方案发送至终端设备。该图像补充采集方案包括不满足要求的二维图像，以及该二维图像不满足要求的原因“照片过度曝光”。用户根据上述信息，可以很容易的确定需要补充采集的二维图像，以及补充采集二维图像时的注意事项，例如，降低拍摄环境中的光照强度，或者通过调节摄像头的光圈降低曝光度，以确保补充采集的二维图像符合图像补充采集方案的要求。
需要指出的是，终端设备采集的二维图像还可能存在其它缺陷，例如，分辨率过低、照片背景不符合要求等，在此不再一一列举。
步骤S907：终端设备根据所述图像补充采集方案，补充采集重建对象的二维图像。
终端设备在接收到图像补充采集方案后，根据该图像补充采集方案，补充采集重建对象的二维图像。完成图像补充采集后，将采集的二维图像发送至服务器设备。需要指出的是，此时采集的二维图像包括终端设备根据图像采集方案初次采集的二维图像，以及根据图像采集方案补充采集的二维图像。
在一种可能的实施例中，终端设备在补充采集重建对象的二维图像之后，还可以将补充采集的二维图像的摘要信息发送至服务器设备，服务器设备判断该补充采集的二维图像是否满足要求。
本申请实施例在根据图像采集方案完成二维图像的采集后，终端设备和服务器设备对采集的二维图像的数量和质量情况进一步沟通，可以进一步提高一次重建成功率。
可理解，终端设备在采用上述方法完成二维图像的采集后，需要将采集的二维图像发送至服务器器设备，服务器设备根据二维图像执行3D模型重建。具体包括以下步骤：步骤S1201：终端设备向服务器设备发送采集的二维图像。
终端设备在完成图像采集后，将采集的二维图像发送至服务器设备，以便服务器设备根据所述二维图像执行3D模型重建操作。
需要指出的是，若步骤S1201在图9所示的步骤S907之后执行，则终端设备向服务器设备发送的二维图像包括终端设备根据图像采集方案初次采集的二维图像，以及根据图像补充采集方案补充采集的二维图像。
步骤S1202：服务器设备根据所述二维图像，执行三维模型重建操作，生成三维模型。
服务器设备接收到终端设备发送的二维图像后，对所述二维图像，执行3D模型重建操作，生成3D模型。在一种可选实施例中，所述3D模型重建操作可以为photogrammetry pipeline计算。当然，本申请实施例对3D模型重建工具不做限制，本领域技术人员可以基于其它工具完成3D模型重建。
另外，在服务器设备执行3D模型重建的过程中，可以按照预设的时间间隔将3D模型重建的进度发送至终端设备，以便用户实时掌握3D模型重建进度。
步骤S1203：服务器设备向终端设备发送所述三维模型。
在完成3D模型重建后，服务器设备将3D模型发送至终端设备，至此，完成3D模型重建。该3D模型可以为obj等3D模型专用格式文件。该文件后续可用于3D打印、动画制作、教学、产品设计等过程。
具体实现中，本申请实施例还提供了一种终端设备，所述终端设备包括一个或多个摄像头、处理器、存储器，以及一个或多个计算机程序，其中所述一个或多个计算机程序被存储在所述存储器中，所述一个或多个计算机程序包括指令，当所述指令被所述终端设备执行时，使得所述终端设备执行上述方法实施例中的部分或全部步骤。
具体实现中，本申请实施例还提供了一种服务器设备，所述服务器设备包括一个或多个处理器、存储器，以及一个或多个计算机程序，其中所述一个或多个计算机程序被存储在所述存储器中，所述一个或多个计算机程序包括指令，当所述指令被所述终端设备执行时，使得所述终端设备执行上述方法实施例中的部分或全部步骤。
具体实现中，本申请还提供一种计算机存储介质，其中，该计算机存储介质可存储有程序，该程序执行时可包括本申请提供的各实施例中的部分或全部步骤。所述的存储介质可为磁碟、光盘、只读存储记忆体(英文：read-only memory，简称：ROM)或随机存储记忆体(英文：random access memory，简称：RAM)等。
具体实现中，本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包含可执行指令，当所述可执行指令在计算机上执行时，使得计算机执行上述方法实施例中的部分或全部步骤。
本申请实施例中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示单独存在A、同时存在A和B、单独存在B的情况。其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项”及其类似表达，是指的这些项中的任意组合，包括单项或复数项的任意组合。例如，a，b和c中的至少一项可以表示：a,b,c,a-b,a-c,b-c,或a-b-c，其中a,b,c可以是单个，也可以是多个。
本领域普通技术人员可以意识到，本文中公开的实施例中描述的各单元及算法步骤，能够以电子硬件、计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本发明所提供的几个实施例中，任一功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，简称ROM)、随机存取存储器(random  access memory，简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。本发明的保护范围应以所述权利要求的保护范围为准。

Claims (18)

  1. 一种三维模型重建方法，其特征在于，应用于终端设备，所述方法包括：
    向服务器设备发送三维模型重建指标信息，所述三维模型重建指标信息用于表征三维模型重建要求；
    接收所述服务器设备发送的图像采集方案，所述图像采集方案用于指导重建对象的二维图像的采集；
    根据所述图像采集方案，采集所述重建对象的二维图像，所述二维图像用于三维模型重建。
  2. 根据权利要求1所述的方法，其特征在于，所述图像采集方案包括图像采集引导程序；
    所述根据所述图像采集方案，采集重建对象的二维图像，包括：根据所述图像采集引导程序的引导，采集所述重建对象的二维图像。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述图像采集引导程序的引导，采集所述重建对象的二维图像，包括：
    输出移动方向指引信息，所述移动方向指引信息用于提示向目标位置移动；
    响应于用户输入的图像采集指令，采集所述重建对象的二维图像。
  4. 根据权利要求3所述的方法，其特征在于，所述图像采集引导程序包括图像采集顺序，所述输出移动方向指引信息，包括：
    根据所述图像采集顺序，在完成第一采集位置的第一二维图像采集后，输出第一采集位置至第二采集位置的移动方向指引信息，所述第一采集位置至第二采集位置的移动方向指引信息用于提示向第二采集位置移动。
  5. 根据权利要求3所述的方法，其特征在于，还包括：
    当判断移动至所述目标位置时，输出到达目标位置提示信息。
  6. 根据权利要求2所述的方法，其特征在于，所述根据所述图像采集引导程序的引导，采集所述重建对象的二维图像，包括：
    通过所述图像采集引导程序控制机械臂带动所述终端设备移动至目标位置，采集所述重建对象的二维图像。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，还包括：
    展示完成采集的二维图像的预览图像。
  8. 根据权利要求1所述的方法，其特征在于，还包括：
    对采集的所述二维图像进行预处理，获得所述二维图像的摘要信息；
    向所述服务器设备发送所述二维图像的摘要信息，所述摘要信息用于判断采集的所述二维图像是否满足三维模型的重建要求；
    响应于所述服务器设备发送的图像补充采集方案，根据所述图像补充采集方案，补充采集所述重建对象的二维图像；或者，
    接收所述服务器设备发送的二维图像满足条件指令，所述二维图像满足条件指令用于表征采集的所述二维图像可以满足三维模型的重建要求。
  9. 根据权利要求8所述的方法，其特征在于，所述图像补充采集方案包括缺陷提示信息，所述缺陷提示信息用于提示存在缺陷的原因。
  10. 根据权利要求1所述的方法，其特征在于，所述向服务器设备发送三维模型重建指标信息，包括：
    响应于用户输入的三维模型重建指标输入信息和/或三维模型重建指标选择信息，向服务器设备发送三维模型重建指标信息，其中，所述三维模型重建指标信息与所述三维模型重建指标输入信息和/或三维模型重建指标选择信息相对应。
  11. 根据权利要求1所述的方法，其特征在于，所述三维模型重建指标信息包括质量指标信息和/或物体指标信息，所述质量指标信息用于表征需要重建的三维模型的质量，所述物体指标信息用于表征需要重建的三维模型的尺寸。
  12. 根据权利要求11所述的方法，其特征在于，所述质量指标信息包括需要重建的三维模型的平均差MSE和/或交并集交叉比例IoU；和/或，
    所述物体指标信息包括需要重建的三维模型的长宽高和/或需要重建的三维模型对应的球体的直径。
  13. 根据权利要求11所述的方法，其特征在于，所述三维模型重建指标信息还包括性能指标信息，所述性能指标信息用于表征三维模型重建过程中用户期望耗费的资源。
  14. 根据权利要求12所述的方法，其特征在于，还包括：
    接收所述服务器设备发送的性能指标不满足三维模型重建要求指令，所述性能指标不满足三维模型重建要求指令用于表征用户期望耗费的资源不满足三维模型重建要求。
  15. 根据权利要求1所述的方法，其特征在于，还包括：
    接收所述服务器设备发送的预估性能信息，所述预估性能信息包括三维模型重建过程中预估需要耗费的资源。
  16. 根据权利要求1所述的方法，其特征在于，所述图像采集方案包括文本类图像采集引导信息和/或音视频图像采集引导信息。
  17. 一种终端设备，其特征在于，包括：
    一个或多个摄像头；
    一个或多个处理器；
    存储器；
    以及一个或多个计算机程序，其中所述一个或多个计算机程序被存储在所述存储器中，所述一个或多个计算机程序包括指令，当所述指令被所述一个或多个处理器执行时，使得所述终端设备执行权利要求1至16中任意一项所述的方法。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质包括存储的程序，其中，在所述程序运行时控制所述计算机可读存储介质所在设备执行权利要求1至16中任意一项所述的方法。
PCT/CN2021/138868 2020-12-25 2021-12-16 三维模型重建方法、设备和存储介质 WO2022135272A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/258,716 US20240046560A1 (en) 2020-12-25 2021-12-16 Three-Dimensional Model Reconstruction Method, Device, and Storage Medium
EP21909268.1A EP4250238A4 (en) 2020-12-25 2021-12-16 METHOD, DEVICE AND STORAGE MEDIUM FOR RECONSTRUCTING A THREE-DIMENSIONAL MODEL

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011585146.9A CN114697516B (zh) 2020-12-25 2020-12-25 三维模型重建方法、设备和存储介质
CN202011585146.9 2020-12-25

Publications (1)

Publication Number Publication Date
WO2022135272A1 true WO2022135272A1 (zh) 2022-06-30

Family

ID=82129550

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/138868 WO2022135272A1 (zh) 2020-12-25 2021-12-16 三维模型重建方法、设备和存储介质

Country Status (4)

Country Link
US (1) US20240046560A1 (zh)
EP (1) EP4250238A4 (zh)
CN (1) CN114697516B (zh)
WO (1) WO2022135272A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116486008A (zh) * 2023-04-12 2023-07-25 荣耀终端有限公司 一种三维重建方法、显示方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107672182A (zh) * 2017-11-13 2018-02-09 南京中高知识产权股份有限公司 基于云服务器的3d打印系统及3d打印方法
US20180059631A1 (en) * 2016-08-23 2018-03-01 Echostar Technologies L.L.C. Dynamic 3d object recognition and printing
CN109410322A (zh) * 2018-10-23 2019-03-01 北京旷视科技有限公司 三维对象建模方法、装置及电子设备
CN110769240A (zh) * 2019-08-23 2020-02-07 上海亦我信息技术有限公司 基于拍照的3d建模系统及方法、自动3d建模装置及方法
CN110874861A (zh) * 2019-11-22 2020-03-10 武汉中天云迪科技有限公司 一种三维数字化图像采集方法及设备

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3841401B2 (ja) * 2001-09-26 2006-11-01 株式会社東芝 構内案内装置、サーバ装置およびプログラム
DE102005055825A1 (de) * 2005-11-23 2007-05-24 Basf Ag Vorrichtung und Verfahren für die automatische Bestimmung der individuellen dreidimensionalen Partikelform
US8488040B2 (en) * 2010-06-18 2013-07-16 Microsoft Corporation Mobile and server-side computational photography
JP5067476B2 (ja) * 2010-12-28 2012-11-07 カシオ計算機株式会社 三次元モデル作成システム
JP5067477B2 (ja) * 2010-12-28 2012-11-07 カシオ計算機株式会社 撮像パラメータ取得装置、撮像パラメータ取得方法、及び、プログラム
JP2015507860A (ja) * 2011-12-07 2015-03-12 インテル コーポレイション 画像キャプチャのガイド
CN104994369B (zh) * 2013-12-04 2018-08-21 南京中兴软件有限责任公司 一种图像处理方法、用户终端、图像处理终端及系统
KR101413393B1 (ko) * 2014-02-25 2014-06-27 송승욱 3차원 모델링을 위한 촬상장치 및 그 제어방법
US9510757B2 (en) * 2014-05-07 2016-12-06 Align Technology, Inc. Identification of areas of interest during intraoral scans
CN105260605B (zh) * 2015-10-14 2019-04-09 中国石油天然气集团公司 一种三维地震数据体的处理方法、服务器、客户端及系统
CN107026973B (zh) * 2016-02-02 2020-03-13 株式会社摩如富 图像处理装置、图像处理方法与摄影辅助器材
EP3422955B1 (en) * 2016-02-29 2023-10-18 Packsize International, LLC System and method for assisted 3d scanning
CN106604016A (zh) * 2017-01-26 2017-04-26 上海图漾信息科技有限公司 立体视频采集系统
CN107809598B (zh) * 2017-11-16 2019-11-29 维沃移动通信有限公司 一种拍摄方法、移动终端及服务器
CN108182726A (zh) * 2017-12-29 2018-06-19 努比亚技术有限公司 三维重建方法、云端服务器及计算机可读存储介质
CN208424630U (zh) * 2018-04-20 2019-01-22 深圳尊豪网络科技股份有限公司 一种全景大数据应用监测管控系统
CN108566514A (zh) * 2018-04-20 2018-09-21 Oppo广东移动通信有限公司 图像合成方法和装置、设备、计算机可读存储介质
CN108712604B (zh) * 2018-05-07 2022-02-01 维沃移动通信有限公司 一种全景拍摄方法及移动终端
CN108833772A (zh) * 2018-05-30 2018-11-16 深圳奥比中光科技有限公司 基于深度相机的拍照引导系统及方法
MX2021002767A (es) * 2018-09-19 2021-05-31 Artec Europe S A R L Escaner tridimensional con retroalimentacion de recopilacion de datos.
CN111669604A (zh) * 2019-03-07 2020-09-15 阿里巴巴集团控股有限公司 一种采集设备设置方法及装置、终端、采集系统、设备
CN110348291A (zh) * 2019-05-28 2019-10-18 华为技术有限公司 一种场景识别方法、一种场景识别装置及一种电子设备
CN110782521A (zh) * 2019-09-06 2020-02-11 重庆东渝中能实业有限公司 移动端三维重建与模型修复方法及系统
CN110853133A (zh) * 2019-10-25 2020-02-28 深圳奥比中光科技有限公司 重建人体三维模型的方法、装置、系统和可读存储介质
CN110998671B (zh) * 2019-11-22 2024-04-02 驭势科技（浙江）有限公司 三维重建方法、装置、系统和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180059631A1 (en) * 2016-08-23 2018-03-01 Echostar Technologies L.L.C. Dynamic 3d object recognition and printing
CN107672182A (zh) * 2017-11-13 2018-02-09 南京中高知识产权股份有限公司 基于云服务器的3d打印系统及3d打印方法
CN109410322A (zh) * 2018-10-23 2019-03-01 北京旷视科技有限公司 三维对象建模方法、装置及电子设备
CN110769240A (zh) * 2019-08-23 2020-02-07 上海亦我信息技术有限公司 基于拍照的3d建模系统及方法、自动3d建模装置及方法
CN110874861A (zh) * 2019-11-22 2020-03-10 武汉中天云迪科技有限公司 一种三维数字化图像采集方法及设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4250238A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116486008A (zh) * 2023-04-12 2023-07-25 荣耀终端有限公司 一种三维重建方法、显示方法及电子设备
CN116486008B (zh) * 2023-04-12 2023-12-12 荣耀终端有限公司 一种三维重建方法、显示方法及电子设备

Also Published As

Publication number Publication date
CN114697516A (zh) 2022-07-01
EP4250238A4 (en) 2024-04-17
EP4250238A1 (en) 2023-09-27
US20240046560A1 (en) 2024-02-08
CN114697516B (zh) 2023-11-10

Similar Documents

Publication Publication Date Title
WO2021013230A1 (zh) 机器人的控制方法、机器人、终端、服务器及控制系统
CN111327814A (zh) 一种图像处理的方法及电子设备
CN110072070A (zh) 一种多路录像方法及设备
WO2021169394A1 (zh) 基于深度的人体图像美化方法及电子设备
CN109559270A (zh) 一种图像处理方法及电子设备
WO2022017261A1 (zh) 图像合成方法和电子设备
CN112262563A (zh) 图像处理方法及电子设备
CN111741283A (zh) 图像处理的装置和方法
WO2022052620A1 (zh) 图像生成方法及电子设备
CN115439606A (zh) 三维重建方法、图形界面、系统及相关装置
WO2022001806A1 (zh) 图像变换方法和装置
WO2023284715A1 (zh) 一种物体重建方法以及相关设备
WO2020192209A1 (zh) 一种基于Dual Camera+TOF的大光圈虚化方法
CN110458902A (zh) 3d光照估计方法及电子设备
CN110138999B (zh) 一种用于移动终端的证件扫描方法及装置
WO2022143921A1 (zh) 一种图像重建方法、相关装置及系统
WO2022135272A1 (zh) 三维模型重建方法、设备和存储介质
CN115147451A (zh) 目标跟踪方法及其装置
CN115032640B (zh) 手势识别方法和终端设备
CN114283195B (zh) 生成动态图像的方法、电子设备及可读存储介质
WO2022078116A1 (zh) 笔刷效果图生成方法、图像编辑方法、设备和存储介质
WO2022017270A1 (zh) 外表分析的方法和电子设备
WO2022033344A1 (zh) 视频防抖方法、终端设备和计算机可读存储介质
CN115393676A (zh) 手势控制优化方法、装置、终端和存储介质
CN115150542A (zh) 一种视频防抖方法及相关设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21909268

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18258716

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2021909268

Country of ref document: EP

Effective date: 20230620

NENP Non-entry into the national phase

Ref country code: DE