WO2022142908A1 - 三维模型生成方法、xr设备及存储介质 - Google Patents

三维模型生成方法、xr设备及存储介质 Download PDF

Info

Publication number
WO2022142908A1
WO2022142908A1 PCT/CN2021/133183 CN2021133183W WO2022142908A1 WO 2022142908 A1 WO2022142908 A1 WO 2022142908A1 CN 2021133183 W CN2021133183 W CN 2021133183W WO 2022142908 A1 WO2022142908 A1 WO 2022142908A1
Authority
WO
WIPO (PCT)
Prior art keywords
dimensional model
dimensional
model
preset
target
Prior art date
Application number
PCT/CN2021/133183
Other languages
English (en)
French (fr)
Inventor
卓龙
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2022142908A1 publication Critical patent/WO2022142908A1/zh

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/006—Mixed reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation

Definitions

  • the present disclosure relates to the technical field of model construction, and in particular, to a method for generating a three-dimensional model, an XR device and a storage medium.
  • Extended Reality refers to a combination of real and virtual, human-computer interactive environment generated by computer technology and wearable devices, including Augmented Reality (AR), Virtual Reality (VR), Mixed Reality (MR) ) and other forms.
  • AR Augmented Reality
  • VR Virtual Reality
  • MR Mixed Reality
  • the real world is seamlessly transformed into a fully immersive virtual world, and users can choose the extent of extending the real world to the virtual world according to their own wishes.
  • the 3D data of the target object is scanned by a 3D scanning device, and the user uses a flat-panel display to edit the 3D model constructed according to the 3D data of the target object, which makes the imaging process of the 3D model of the target object cumbersome, and it is impossible to generate a 3D model in real time. model, which reduces the development efficiency of a 3D scene composed of multiple 3D models.
  • the present disclosure provides a three-dimensional model generation method, an XR device and a storage medium, aiming to generate a three-dimensional model of a target object in real time and quickly, and optimize the imaging process of the three-dimensional model, thereby improving the development efficiency of a three-dimensional scene.
  • an embodiment of the present disclosure provides a method for generating a 3D model, which is applied to an extended reality XR device, including: acquiring a 3D data stream of a target object sent by a 3D scanning device during a scanning process, and constructing the target object according to the 3D data stream calculate the matching degree between the three-dimensional model and multiple preset three-dimensional models, and determine the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees; update the three-dimensional model according to the preset three-dimensional model matching the three-dimensional model model to obtain the target 3D model of the target object.
  • embodiments of the present disclosure further provide an XR device, the XR device includes a processor, a memory, a computer program stored on the memory and executable by the processor, and a computer program for implementing connection and communication between the processor and the memory
  • the data bus wherein when the computer program is executed by the processor, implements the steps of any one of the three-dimensional model generation methods provided by the embodiments of the present disclosure.
  • embodiments of the present disclosure further provide a storage medium for computer-readable storage, where the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to achieve The steps of any of the three-dimensional model generation methods provided by the embodiments of the present disclosure.
  • FIG. 1 is a schematic flowchart of steps of a method for generating a three-dimensional model according to an embodiment of the present disclosure
  • Fig. 2 is a schematic flow chart of sub-steps of the three-dimensional model generation method in Fig. 1;
  • FIG. 3 is a schematic diagram of a scene for implementing the method for generating a 3D model provided by an embodiment of the present disclosure
  • FIG. 4 is a schematic flowchart of steps of another three-dimensional model generation method provided by an embodiment of the present disclosure
  • FIG. 5 is a schematic structural block diagram of an XR device according to an embodiment of the present disclosure.
  • Embodiments of the present disclosure provide a method for generating a three-dimensional model, an XR device, and a storage medium.
  • the three-dimensional model generation method can be applied to the XR extended reality device.
  • the XR device can get rid of the constraints of an external computer and realize the leap from the PC terminal to the mobile terminal.
  • the XR device includes VR devices, AR devices, MR devices and/or wearables
  • the XR device is HoloSuit (the world's first full-body motion capture XR device that realizes wireless two-way feedback).
  • the XR device includes a somatosensory suit, a pair of gloves and a pair of sports pants.
  • FIG. 1 is a schematic flowchart of steps of a method for generating a three-dimensional model according to an embodiment of the present disclosure.
  • the three-dimensional model generation method includes steps S101 to S103.
  • Step S101 acquiring a three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process, and constructing a three-dimensional model of the target object according to the three-dimensional data stream.
  • three-dimensional data of a target object is obtained by scanning a three-dimensional scanning device, and a user uses a flat display to edit a three-dimensional model constructed according to the three-dimensional data of the target object.
  • the embodiment of the present disclosure obtains the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process through the XR device, and uses the XR device to perform model imaging on the three-dimensional data stream of the target object in real time, which can quickly generate the target object's three-dimensional data stream.
  • 3D model improve the development efficiency of 3D scene composed of multiple 3D models.
  • the target object can be an object, a human body, an environment, and the like.
  • the target object can be a vehicle, a sofa, a room, etc., which can be set according to the actual situation.
  • the 3D data stream includes 3D data that is continuously sent.
  • the XR device can build a 3D model of the target object in real time based on the 3D data that is continuously sent. That is, the 3D model of the target object is in the process of continuous improvement with the stacking of the 3D data stream. middle.
  • the three-dimensional model referred to in this embodiment includes an incomplete three-dimensional model, for example, a three-dimensional model with a construction progress of 50%.
  • the imaging speed of the 3D model optimizes the imaging process of the 3D model.
  • the 3D scanning device includes 3D scanners, aerial photography drones, detection radars, super-depth cameras and other equipment.
  • the 3D scanning device is connected to XR equipment in communication, such as through a 5G network connection, which can transmit 3D data in real time and quickly.
  • the target object is scanned by the 3D scanning device, and the 3D data stream of the scanned target object is sent to the XR device in real time.
  • the XR device can obtain the 3D data stream of the target object collected by the 3D scanning device in real time and, The flow builds a 3D model of the target object.
  • the 3D model of the target object can be generated in real time and quickly, which is beneficial to improve the development efficiency of the 3D model.
  • the target object can be scanned by a 3-dimensional scanner (3 Dimensional Scanner) to obtain the three-dimensional data of the target object.
  • the 3D scanner sends the scanned 3D data to the XR device in real time, so that the XR device can obtain the 3D data stream of the target object and build a 3D model of the target object according to the 3D data stream.
  • the 3D scanner is also called 3 Dimensional Digitizer.
  • the 3D scanner communicates with the XR equipment, for example, through the 5G network signal to realize the rapid synchronous transmission of 3D data, and accurately and quickly according to the target through the XR equipment.
  • the three-dimensional data of the object performs three-dimensional modeling on the target object to obtain a three-dimensional model.
  • the target object For example, scan the target object through a 3D scanner, convert the stereoscopic color information of the target object in the real world into a digital signal that can be directly processed by the computer, and obtain the 3D space coordinates of each sampling point on the surface of the object in space.
  • the 3D scanner also includes a color scanner.
  • the color scanner can output the color texture map of the surface of the object, and obtain a digital model file containing the three-dimensional space coordinates and color of each sampling point on the surface of the object, so that the three-dimensional image constructed by the XR equipment can be obtained. Models are more realistic.
  • the depth measurement of the target object can also be obtained through the medium of laser or ultrasonic wave, and the three-dimensional data of the target object can also be obtained.
  • the rangefinder sends a depth measurement signal to the target object.
  • the spatial position of the object surface of the target object can be obtained, thereby obtaining the three-dimensional data of the target object.
  • the three-dimensional data of the target object can be obtained conveniently and quickly through the radar principle, and the practicability is high.
  • a super-depth-of-field camera is installed in the space where the target object is located, and the three-dimensional data includes a clear image captured by the super-depth-of-field camera.
  • the focal length of the super depth of field camera is adjusted to photograph different positions of the target object, so that the super depth of field camera can obtain clear images of different position regions of the target object.
  • the XR equipment obtains multiple clear images sent by the super depth of field camera, and obtains the shooting time point of each clear image, and determines the stitching sequence of each clear image according to the shooting time point of each clear image; Stitching sequence, stitching each clear image to get a 3D model of the target object.
  • the splicing sequence of each clear image is determined according to the sequence of the shooting time points of each clear image, wherein the earlier the shooting time point is, the earlier the splicing sequence is, and the later the shooting time point is, the earlier the splicing sequence is. further back. It should be noted that clear images of different position areas of the target object are captured by the super-depth camera, and the clear images are sent to the XR device, so that the XR device can easily construct the target object based on the clear images of different position areas of the target object. 3D model.
  • Step S102 calculating the matching degree between the three-dimensional model and multiple preset three-dimensional models, and determining the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees.
  • a plurality of preset 3D models are pre-stored in the XR device.
  • the preset 3D models are for building a complete 3D model, and of course, it can also be used for building an incomplete 3D model.
  • the matching degree between the three-dimensional model of the target object and the plurality of preset three-dimensional models is calculated, and the matching degree corresponding to each preset three-dimensional model is obtained.
  • At least one preset three-dimensional model can be determined according to the plurality of matching degrees, and a matching relationship between the three-dimensional model of the target object and the at least one preset three-dimensional model can be established.
  • the database stores a plurality of preset three-dimensional models, and the three-dimensional models are sent to the database to compare the three-dimensional model with each preset three-dimensional model stored in the database to obtain multiple matching degrees. Corresponds to the preset 3D model.
  • determining a preset three-dimensional model matching the three-dimensional model according to multiple matching degrees includes: sub-steps S1021 to S1022 .
  • Sub-step S1021 Select at least one target matching degree from the multiple matching degrees.
  • the multiple matching degrees are sorted, and at least one target matching degree is selected according to the sorting order; and/or, from the multiple matching degrees Select at least one target matching degree greater than or equal to the preset matching degree.
  • the multiple matching degrees may be sorted by size, and at least one (for example, a preset number) of target matching degrees is selected in descending order.
  • the matching degree of at least one selected target is greater than or equal to the preset matching degree, and the preset matching degree can be set flexibly, for example, the preset matching degree is 90%, so as to ensure the accuracy of the preset three-dimensional model corresponding to the selected target matching degree .
  • At least one target matching degree may also be randomly selected from multiple matching degrees, or at least one target matching degree may be selected according to other rules easily conceived by those skilled in the art, which is not specifically limited in this embodiment.
  • the preset matching degree is determined according to the construction progress of the three-dimensional model, and the construction progress can be determined according to the receiving progress of the three-dimensional data stream. Since the three-dimensional model of the target object can be constructed according to the acquired three-dimensional data stream in real time, the construction progress is The error with the receiving progress of the three-dimensional data stream is small. It should be noted that, the greater the construction progress of the three-dimensional model, the greater the preset matching degree, the smaller the construction progress of the three-dimensional model, and the smaller the preset matching degree.
  • the relationship between the receiving progress, the building progress, and the preset matching degree can be set by the user, and optionally, can be set through the mapping relationship table. For example, when the receiving progress of the three-dimensional data stream is 30%, it is determined through the mapping relationship table that the construction progress of the three-dimensional model is 25%, and the preset matching degree is 20%.
  • Sub-step S1022 Determine a preset three-dimensional model corresponding to at least one target matching degree as a preset three-dimensional model matching the three-dimensional model.
  • the matching degree corresponds to the preset three-dimensional model
  • the target matching degree also corresponds to the preset three-dimensional model
  • the preset three-dimensional model corresponding to at least one target matching degree is determined as the preset three-dimensional model matching the three-dimensional model, that is, the target object is established.
  • the multiple matching degrees are sorted, and at least one target matching degree is selected according to the sorting order; the preset three-dimensional model corresponding to the at least one target matching degree is displayed by the display device; The triggering operation of the three-dimensional model determines a preset three-dimensional model matching the three-dimensional model from at least one preset three-dimensional model.
  • the sorting order may be in descending order, which is convenient for the user to select the preset 3D model and match the 3D model, which speeds up the imaging process of the 3D model.
  • Step S103 Update the three-dimensional model according to the preset three-dimensional model matched with the three-dimensional model to obtain the target three-dimensional model of the target object.
  • the 3D model can generate the target 3D model of the target object in real time and quickly, optimize the imaging process of the existing 3D model, and greatly improve the development efficiency of the 3D scene.
  • the XR device includes a display device, such as a multi-faceted screen, smart glasses, smart helmet, and the like. Display the preset 3D model matching the 3D model through the display device, select the preset 3D model according to the received confirmation instruction triggered by the user, and determine whether to update the 3D model according to the preset 3D model matching the 3D model, so as to obtain the target The target 3D model of the object.
  • a display device such as a multi-faceted screen, smart glasses, smart helmet, and the like.
  • the target three-dimensional model is displayed; and the displayed target three-dimensional model is edited according to an editing instruction triggered by the user.
  • the XR equipment includes a display device and a control device, and the control device includes a handheld interactive device, such as a joystick, a remote control, and a terminal.
  • the display device displays the target three-dimensional model
  • the control device is used to edit the displayed target three-dimensional model, generate editing instructions based on the user's triggering operation on the control device, and edit the displayed target according to the editing instructions triggered by the user.
  • 3D model for editing The editing of the target three-dimensional model can be realized, and the user does not need to switch devices to edit the three-dimensional model, which optimizes the imaging process of the existing three-dimensional model and greatly improves the development efficiency of the three-dimensional scene.
  • the editing instructions include model adjustment instructions.
  • the model adjustment parameters of the position, color, texture, size and/or shape of the displayed target 3D model are determined; according to the model adjustment parameters, the displayed target 3D model is adjusted.
  • the user can trigger the model adjustment instruction through the control device to adjust the position, color, texture, size and/or shape of the target 3D model, etc.
  • the XR device generates model adjustment parameters based on the model adjustment instruction, and adjusts the parameters according to the model.
  • the adjustment of the displayed target 3D model is simple and easy to understand. Unlike editing the 3D model through a flat screen, editing the 3D model through XR equipment can improve the immersion of the virtual world, thereby improving the user's editing experience.
  • the editing instructions include model combining instructions.
  • the model combination instruction triggered by the user at least one preset 3D model is selected, and the model combination parameters corresponding to the at least one preset 3D model are determined; according to the model combination parameters, the at least one preset 3D model is combined with the displayed target 3D model .
  • a plurality of preset three-dimensional models are stored in the database.
  • the user can trigger the model combination instruction through the control device, so as to select at least one preset 3D model from the database, and determine how to combine the selected preset 3D model with the target 3D model.
  • the operation of the combination process is simple. It can quickly build a virtual scene that is close to the real effect in the virtual world by building blocks. Unlike editing 3D models through a flat screen, the combination of models through XR equipment can restore the user's experience in the virtual world to the greatest extent. immersion, thereby enhancing the user experience.
  • the target three-dimensional model of the target object is obtained, the target three-dimensional model is added as a preset three-dimensional model to a plurality of preset three-dimensional models.
  • the target 3D model is stored in a specified file stored in a database, and the specified file stores multiple preset 3D models, thereby expanding the number of preset 3D models in the database and facilitating matching and calling of preset 3D models.
  • FIG. 3 is a schematic diagram of a scene for implementing the method for generating a three-dimensional model provided by an embodiment of the present disclosure.
  • the three-dimensional scanning device 20 scans the target object 10 to obtain three-dimensional data of the target object 10 .
  • the three-dimensional scanning device 20 collects the collected three-dimensional data of the target object 10 into a three-dimensional data stream and sends it to the XR device 30 .
  • the XR device 30 receives the three-dimensional data stream of the target object 10 sent by the three-dimensional scanning device 20, and constructs a three-dimensional model of the target object 10 according to the three-dimensional data stream.
  • the XR device 30 calculates the degree of matching between the three-dimensional model and a plurality of preset three-dimensional models, A preset three-dimensional model matching the three-dimensional model is determined according to the multiple matching degrees, and the three-dimensional model is updated according to the preset three-dimensional model matching the three-dimensional model to obtain the target three-dimensional model of the target object 10 .
  • the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process is obtained, and the three-dimensional model of the target object is constructed according to the three-dimensional data stream, and the relationship between the three-dimensional model and a plurality of preset three-dimensional models is calculated.
  • the matching degree is determined, and a preset three-dimensional model matching the three-dimensional model is determined according to the multiple matching degrees, and the three-dimensional model is updated according to the preset three-dimensional model matching the three-dimensional model to obtain the target three-dimensional model of the target object.
  • the combination of XR technology and model imaging is realized, and the preset 3D model can be matched to the target 3D model of the target object in real time and quickly, which optimizes the imaging process of the existing 3D model and greatly improves the development efficiency of 3D scenes.
  • FIG. 4 is a schematic flowchart of steps of another three-dimensional model generation method provided by an embodiment of the present disclosure.
  • the three-dimensional model generation method includes steps S201 to S206.
  • Step S201 acquiring a three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process, and constructing a three-dimensional model of the target object according to the three-dimensional data stream.
  • the target object can be an object, a human body, an environment, and the like.
  • the target object can be a vehicle, a sofa, a room, etc., which can be set according to the actual situation.
  • the 3D data stream includes 3D data that is continuously sent.
  • the XR device can build a 3D model of the target object in real time based on the 3D data that is continuously sent. That is, the 3D model of the target object is in the process of continuous improvement with the stacking of the 3D data stream. middle.
  • the three-dimensional model referred to in this embodiment includes an incomplete three-dimensional model, for example, a three-dimensional model with a construction progress of 50%.
  • the rapid imaging of 3D models optimizes the imaging process of 3D models.
  • the 3D scanning device includes 3D scanners, aerial photography drones, detection radars, super-depth cameras and other equipment.
  • the 3D scanning device is connected to XR equipment in communication, such as through a 5G network connection, which can transmit 3D data in real time and quickly.
  • the target object is scanned by the 3D scanning device, and the 3D data stream of the scanned target object is sent to the XR device in real time.
  • the XR device can obtain the 3D data stream of the target object collected by the 3D scanning device in real time and, The flow builds a 3D model of the target object.
  • the three-dimensional model of the target object is generated in real time and quickly, which is beneficial to improve the development efficiency of the three-dimensional model.
  • Step S202 calculating the degree of matching between the three-dimensional model and a plurality of preset three-dimensional models.
  • a plurality of preset 3D models are pre-stored in the XR device.
  • the preset 3D models are for building a complete 3D model, and of course, it can also be used for building an incomplete 3D model.
  • the matching degree between the three-dimensional model of the target object and the plurality of preset three-dimensional models is calculated, and the matching degree corresponding to each preset three-dimensional model is obtained.
  • Step S203 If the multiple matching degrees are all smaller than the preset matching degrees, continue to acquire the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process.
  • the multiple matching degrees are less than the preset matching degree, that is, the multiple matching degrees do not include the target matching degree greater than or equal to the preset matching degree, it is considered that the multiple preset 3D models cannot match the 3D model, and the acquisition continues at this time.
  • the 3D scanning device sends the 3D data stream of the target object during the scanning process, so as to continue to build an incomplete 3D model. For example, if the matching degree between the 3D model whose construction progress is 25% and the multiple preset 3D models are all smaller than the preset matching degree, the 3D data stream of the target object sent by the 3D scanning device during the scanning process is continued to be obtained to continue.
  • Generate a 3D model with a build progress of 25% or more eg, a build progress of 30%).
  • Step S204 Update the three-dimensional model according to the continuously obtained three-dimensional data stream.
  • the 3D model is updated to obtain a 3D model with a higher construction progress.
  • the 3D model with a higher construction progress is more complete, which is conducive to the subsequent calculation of the matching degree between the 3D model and multiple preset 3D models. , so as to obtain the matching preset 3D model.
  • the construction progress of the updated 3D model is determined, and when the construction progress is greater than or equal to the preset construction progress, the updated 3D model is confirmed as the target object's construction progress.
  • the target three-dimensional model or, receiving a confirmation instruction triggered by the user, and confirming the updated three-dimensional model as the target three-dimensional model of the target object based on the confirmation instruction.
  • the construction progress can be determined according to the receiving progress of the 3D data stream, and the error between the construction progress and the receiving progress of the 3D data stream is small, and when the construction progress is greater than or equal to the preset construction progress, the updated 3D model is confirmed as the target The target 3D model of the object.
  • the preset construction progress is 99%.
  • the updated 3D model is considered to be a complete 3D model, and the complete 3D model is taken as the target 3D model of the target object, and no subsequent pre-production is required.
  • the user when the user believes that the updated 3D model meets the standard, the user triggers a confirmation instruction through the control device, etc., and the XR device receives the confirmation instruction triggered by the user, and based on the confirmation instruction, confirms the updated 3D model as the target 3D model of the target object.
  • the updated three-dimensional model is modified to obtain a target three-dimensional model of the target object; the target three-dimensional model is added to a plurality of preset three-dimensional models as a preset three-dimensional model.
  • the shape information of the updated 3D model and the coordinate information of multiple lattices are obtained, the abnormal lattice is determined according to the shape information and the coordinate information of the multiple lattices, the coordinate information of each abnormal lattice is adjusted, and the target of the target object is obtained. 3D model.
  • the target coordinate information of the three-dimensional model can be determined according to the shape information and the coordinate information of multiple lattices, and the target coordinate information is compared with the coordinate information of multiple lattices to determine the abnormal lattice.
  • the coordinate information is adjusted to the corresponding target coordinate information, and then the target three-dimensional model of the target object can be obtained.
  • the updated three-dimensional model can be corrected through model correction to improve the integrity of the target three-dimensional model. Adding the target 3D model as a preset 3D model to multiple preset 3D models is convenient for matching and calling the preset 3D models.
  • the XR apparatus includes a graphics processing device, and the updated three-dimensional model is corrected by the graphics processing device.
  • the graphics processing device includes a graphics editing module and a graphics processing module.
  • the graphic editing module can adapt to the model editing parameters, and can edit the model adjustment parameters of the position, color, texture, size and/or shape of the 3D model according to the model editing parameters, or combine at least one preset 3D model with the displayed target according to the model combination parameters. 3D models are assembled.
  • the three-dimensional model can be corrected actively or passively through the graphics processing module.
  • Step S205 Calculate the matching degree between the three-dimensional model and the multiple preset three-dimensional models, and determine the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees.
  • the matching degree between the three-dimensional model of the target object and the plurality of preset three-dimensional models is continuously calculated, and the matching degree corresponding to each preset three-dimensional model is obtained.
  • the 3D model is updated, it becomes more complete, and the construction progress of the 3D model is higher, which is beneficial to determine the preset 3D model that matches the 3D model through multiple matching degrees.
  • the database stores a plurality of preset three-dimensional models, and the three-dimensional models are sent to the database to compare the three-dimensional model with each preset three-dimensional model stored in the database to obtain multiple matching degrees. Corresponds to the preset 3D model.
  • Step S206 Update the three-dimensional model according to the preset three-dimensional model matched with the three-dimensional model to obtain the target three-dimensional model of the target object.
  • the 3D model can intelligently and quickly generate the target 3D model of the target object, optimize the imaging process of the existing 3D model, and greatly improve the development efficiency of the 3D scene.
  • the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process is obtained, and the three-dimensional model of the target object is constructed according to the three-dimensional data stream, and the relationship between the three-dimensional model and a plurality of preset three-dimensional models is calculated.
  • Matching degree if multiple matching degrees are less than the preset matching degree, continue to obtain the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process, update the three-dimensional model according to the continuously obtained three-dimensional data stream, and calculate the three-dimensional model Matching degree with multiple preset three-dimensional models, and determine the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees, update the three-dimensional model according to the preset three-dimensional model matching the three-dimensional model, and obtain the target of the target object 3D model.
  • the combination of XR technology and model imaging is realized, and the preset 3D model can be matched to the target 3D model of the target object in real time and quickly, which optimizes the imaging process of the existing 3D model and greatly improves the development efficiency of 3D scenes.
  • FIG. 5 is a schematic structural block diagram of an XR device according to an embodiment of the present disclosure.
  • the XR extended reality device includes a VR device, an AR device, an MR device, and/or a wearable device, and the like.
  • the XR device is HoloSuit (the world's first full-body motion capture XR device that realizes wireless bidirectional feedback), and the XR device includes a somatosensory suit, a pair of gloves and a pair of sweatpants.
  • the XR device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected through a bus 303, such as an I2C (Inter-integrated Circuit) bus.
  • a bus 303 such as an I2C (Inter-integrated Circuit) bus.
  • the processor 301 is used to provide computing and control capabilities to support the operation of the entire XR device.
  • the processor 301 can be a central processing unit (Central Processing Unit, CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC) ), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like.
  • the memory 302 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) magnetic disk, an optical disk, a U disk, or a removable hard disk, or the like.
  • ROM Read-Only Memory
  • the memory 302 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) magnetic disk, an optical disk, a U disk, or a removable hard disk, or the like.
  • FIG. 5 is only a block diagram of a part of the structure related to the embodiment of the present disclosure, and does not constitute a limitation on the XR device to which the embodiment of the present disclosure is applied.
  • a device may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
  • the processor is configured to run the computer program stored in the memory, and when executing the computer program, implement any one of the three-dimensional model generation methods provided in the embodiments of the present disclosure.
  • the processor is configured to run a computer program stored in the memory, and when executing the computer program, implement the following steps: acquiring the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process, and according to the three-dimensional data
  • the flow constructs a 3D model of the target object; calculates the matching degree between the 3D model and multiple preset 3D models, and determines the preset 3D model matching the 3D model according to the multiple matching degrees; According to the preset 3D model matching the 3D model model, update the 3D model, and obtain the target 3D model of the target object.
  • the processor when determining the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees, is further configured to implement the following steps: select at least one target matching degree from the multiple matching degrees; The preset three-dimensional model corresponding to the target matching degree is determined as the preset three-dimensional model matched with the three-dimensional model.
  • the processor when the processor selects at least one target matching degree from the multiple matching degrees, the processor is further configured to implement the following steps: sorting the multiple matching degrees, and selecting at least one target matching degree according to the sorting order; And/or at least one target matching degree greater than or equal to a preset matching degree is selected from a plurality of matching degrees.
  • the processor is further configured to implement the following step: if the multiple matching degrees are all less than the preset matching degree, continue to acquire the three-dimensional matching degree.
  • the processor is further configured to implement the following steps: determining the construction progress of the updated three-dimensional model, when the construction progress is greater than or equal to the preset construction progress , confirm the updated 3D model as the target 3D model of the target object; or receive a confirmation instruction triggered by the user, and confirm the updated 3D model as the target 3D model of the target object based on the confirmation instruction.
  • the processor is further configured to implement the following steps: correcting the updated three-dimensional model to obtain the target three-dimensional model of the target object; Models are added to multiple preset 3D models as preset 3D models.
  • the processor is further configured to implement the steps of: displaying the target three-dimensional model; and editing the displayed target three-dimensional model according to an editing instruction triggered by the user.
  • the processor when the processor edits the displayed target three-dimensional model according to the editing instruction triggered by the user, the processor is further configured to implement the following steps: determining the position of the displayed target three-dimensional model according to the model adjustment instruction triggered by the user. , color, texture, size and/or shape model adjustment parameters; adjust the displayed target 3D model according to the model adjustment parameters; or select at least one preset 3D model according to the model combination command triggered by the user, and determine at least one Preset model combination parameters corresponding to the three-dimensional model; and combine at least one preset three-dimensional model with the displayed target three-dimensional model according to the model combination parameters.
  • Embodiments of the present disclosure further provide a storage medium for computer-readable storage, where one or more programs are stored in the storage medium, and the one or more programs can be executed by one or more processors, so as to realize the implementation as provided by the present disclosure.
  • the steps of any one of the three-dimensional model generation methods are described in detail below.
  • the storage medium may be an internal storage unit of the XR device described in the foregoing embodiments, such as a hard disk or a memory of the XR device.
  • the storage medium may also be an external storage device of the XR device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (Secure Digital, SD) card, Flash card (Flash Card) and so on.
  • the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process is obtained, and the three-dimensional model of the target object is constructed according to the three-dimensional data stream, and then the three-dimensional model is calculated.
  • Matching degree with multiple preset three-dimensional models and determine the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees, and then update the three-dimensional model according to the preset three-dimensional model matching the three-dimensional model, and obtain the target object's matching degree.
  • 3D model of the target is Using the three-dimensional model generation method, XR device and storage medium provided by the present disclosure, the three-dimensional data stream of the target object sent by the three-dimensional scanning device during the scanning process is obtained, and the three-dimensional model of the target object is constructed according to the three-dimensional data stream, and then the three-dimensional model is calculated.
  • Matching degree with multiple preset three-dimensional models and determine the preset three-dimensional model matching the three-dimensional model according to the multiple matching degrees, and then update the three-
  • the present disclosure combines XR technology with model imaging, without the need for time-consuming and laborious generation of a complete three-dimensional model, and the preset three-dimensional model can be matched to the target three-dimensional model of the target object in real time and quickly, thereby optimizing the imaging process of the existing three-dimensional model. , greatly improving the development efficiency of 3D scenes.
  • Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).
  • computer storage media includes both volatile and nonvolatile implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data flexible, removable and non-removable media.
  • Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices, or may Any other medium used to store desired information and which can be accessed by a computer.
  • communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and can include any information delivery media, as is well known to those of ordinary skill in the art .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Artificial Intelligence (AREA)
  • Architecture (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本公开提供一种三维模型生成方法、XR设备及存储介质。该方法包括：获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型；计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型；根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。

Description

三维模型生成方法、XR设备及存储介质
相关申请的交叉引用
本申请要求享有2020年12月28日提交的名称为“三维模型生成方法、XR设备及存储介质”的中国专利申请CN202011584771.1的优先权，其全部内容通过引用并入本申请中。
技术领域
本公开涉及模型构建的技术领域，尤其涉及一种三维模型生成方法、XR设备及存储介质。
背景技术
扩展现实(Extended Reality，XR)是指通过计算机技术和可穿戴设备产生的一个真实与虚拟组合的、可人机交互的环境，包括增强现实(AR)、虚拟现实(VR)、混合现实(MR)等多种形式。通过AR、VR、MR等多种形式的融合，将现实世界无缝转换为完全沉浸式的虚拟世界，用户能够根据自己的意愿选择将现实世界扩展到虚拟世界的程度。目前，通过三维扫描装置扫描得到目标对象的三维数据，并由用户利用平面显示器对根据目标对象的三维数据构建的三维模型进行编辑，致使目标对象的三维模型的成像过程繁琐，无法实时地生成三维模型，降低了由多个三维模型组成的三维场景的开发效率。
发明内容
本公开提供一种三维模型生成方法、XR设备及存储介质，旨在实时且快速地生成目标对象的三维模型，优化三维模型的成像过程，从而提高三维场景的开发效率。
第一方面，本公开实施例提供一种三维模型生成方法，应用于扩展现实XR设备，包括：获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型；计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型；根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。
第二方面，本公开实施例还提供一种XR设备，该XR设备包括处理器、存储器、存储在存储器上并可被处理器执行的计算机程序以及用于实现处理器和存储器之间的连接通信的数据总线，其中计算机程序被处理器执行时，实现如本公开实施例提供的任一项三维 模型生成方法的步骤。
第三方面，本公开实施例还提供一种存储介质，用于计算机可读存储，该存储介质存储有一个或者多个程序，一个或者多个程序可被一个或者多个处理器执行，以实现如本公开实施例提供的任一项三维模型生成方法的步骤。
附图说明
图1为本公开实施例提供的一种三维模型生成方法的步骤流程示意图；
图2为图1中的三维模型生成方法的子步骤流程示意图；
图3为实施本公开实施例提供的三维模型生成方法的一场景示意图；
图4为本公开实施例提供的另一种三维模型生成方法的步骤流程示意图；
图5为本公开实施例提供的一种XR设备的结构示意框图。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
附图中所示的流程图仅是示例说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解、组合或部分合并，因此实际执行的顺序有可能根据实际情况改变。
应当理解，在此本公开说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本公开。如在本公开说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
本公开实施例提供一种三维模型生成方法、XR设备及存储介质。其中，该三维模型生成方法可应用于XR扩展现实设备中，XR设备能够摆脱外接计算机的束缚，实现从PC端到移动端的跨越，该XR设备包括VR设备、AR设备、MR设备和/或穿戴式设备等，例如XR设备为HoloSuit(世界上第一款实现了无线双向反馈的全身动捕XR设备)，该XR设备包括一件体感衣、一双手套以及一条运动裤。
下面结合附图，对本公开的一些实施方式作详细说明。在不冲突的情况下，下述的实 施例及实施例中的特征可以相互组合。
请参照图1，图1为本公开实施例提供的一种三维模型生成方法的步骤流程示意图。
如图1所示，该三维模型生成方法包括步骤S101至步骤S103。
步骤S101、获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型。
目前，通过三维扫描装置扫描得到目标对象的三维数据，并由用户利用平面显示器对根据目标对象的三维数据构建的三维模型进行编辑。对此，本公开实施例通过XR设备获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并由XR设备实时地对目标对象的三维数据流进行模型成像，能够快速生成目标对象的三维模型，提高由多个三维模型组成的三维场景的开发效率。
目标对象可以为物体、人体、环境等。例如，目标对象可以为车辆、沙发、房间等，可根据实际情况进行设定。三维数据流包括不间断发送的三维数据，XR设备能够实时地根据不间断发送的三维数据构建目标对象的三维模型，即该目标对象的三维模型随着三维数据流的堆叠而处于不断完善的过程中。需要说明的是，本实施例所指的三维模型包括构建不完整的三维模型，例如包括构建进度为50％的三维模型，通过构建不完整的三维模型能够实现模型快速匹配，从而提高构建完整的三维模型的成像速度，优化了三维模型的成像过程。
三维扫描装置包括三维扫描仪、航拍无人机、探测雷达、超景深相机等设备，三维扫描装置与XR设备通信连接，例如通过5G网络连接，能够实时且快速进行三维数据的传输。通过三维扫描装置对目标对象进行扫描，并实时地将扫描得到的目标对象的三维数据流发送至XR设备，XR设备可以获取三维扫描装置实时采集到的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型。通过三维扫描装置与XR设备之间的实时通信，实时且快速地生成目标对象的三维模型，有利于提高三维模型的开发效率。
可以通过三维扫描仪(3 Dimensional Scanner)扫描目标对象，得到目标对象的三维数据。三维扫描仪实时地将扫描得到的三维数据发送至XR设备，以使XR设备获取目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型。其中，三维扫描仪又称为三维数字化仪(3 Dimensional Digitizer)，该三维扫描仪与XR设备通信连接，例如通过5G网络信号实现三维数据的快速同步传输，并通过XR设备精确且快速地根据目标对象的三维数据对目标对象进行三维建模，得到三维模型。
例如，通过三维扫描仪扫描目标对象，将真实世界的目标对象的立体彩色信息转换为 计算机能直接处理的数字信号，得到空间内的物体表面每个采样点的三维空间坐标。将包含物体表面每个采样点的三维空间坐标发送至XR设备，XR设备基于接收的包含物体表面每个采样点的三维空间坐标，构建目标对象的三维模型。需要说明的是，三维扫描仪还包括彩色扫描仪，彩色扫描仪可以输出物体表面色彩纹理贴图，得到包含物体表面每个采样点的三维空间坐标和色彩的数字模型文件，使得XR设备构建的三维模型更加真实。
此外，借助雷达原理，通过激光或超声波等媒介，对目标对象进行深度测量，也可以得到目标对象的三维数据。例如，测距器向目标对象发出深度测量信号，依据深度测量信号的反射时间或相位变化，可以得到目标对象的物体表面的空间位置，从而得到目标对象的三维数据。通过雷达原理能够方便且快速地获取目标对象的三维数据，实用性高。
在一实施例中，目标对象所在的空间中安装有超景深相机，三维数据包括超景深相机拍摄得到的清晰图像。例如，调整该超景深相机的焦距对目标对象的不同位置进行拍摄，以使该超景深相机拍摄得到目标对象的不同位置区域的清晰图像。XR设备获取超景深相机发送到多个清晰图像，并获取每个清晰图像的拍摄时刻点，并根据每个清晰图像的拍摄时刻点，确定每个清晰图像的拼接顺序；根据每个清晰图像的拼接顺序，拼接每个清晰图像，得到目标对象的三维模型。其中，按照每个清晰图像的拍摄时刻点的先后顺序，确定每个清晰图像的拼接顺序，其中，拍摄时刻点越靠前，则拼接顺序越靠前，拍摄时刻点越靠后，则拼接顺序越靠后。需要说明的是，通过超景深相机拍摄目标对象的不同位置区域的清晰图像，并将该清晰图像发送至XR设备，使得XR设备能够基于目标对象的不同位置区域的清晰图像，便捷地构建目标对象的三维模型。
步骤S102、计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型。
XR设备中预存有多个预设三维模型，该预设三维模型为构建完整的三维模型，当然也可以为构建不完整的三维模型。计算目标对象的三维模型与多个预设三维模型之间的匹配度，得到与每个预设三维模型各自对应的匹配度。根据该多个匹配度可以确定至少一个预设三维模型，并建立目标对象的三维模型与至少一个预设三维模型之间的匹配关系。
在一实施例中，数据库存储有多个预设三维模型，将三维模型发送至数据库，以将该三维模型与数据库存储的每个预设三维模型进行对比，得到多个匹配度，该匹配度与预设三维模型相对应。
在一实施例中，如图2所示，根据多个匹配度确定与三维模型匹配的预设三维模型，包括：子步骤S1021至子步骤S1022。
子步骤S1021、从多个匹配度中选取至少一个目标匹配度。
在一实施例中，从多个匹配度中选取至少一个目标匹配度的步骤中，对多个匹配度进行排序，并按照排序顺序选取至少一个目标匹配度；和/或，从多个匹配度中选取大于或等于预设匹配度的至少一个目标匹配度。其中，可以对多个匹配度进行大小排序，并按照从大到小的排序顺序选取至少一个(例如预设数量个)目标匹配度。同时，选取的至少一个目标匹配度大于或等于预设匹配度，预设匹配度可以灵活设置，例如预设匹配度为90％，从而保证选取的目标匹配度对应的预设三维模型的准确性。
需要说明的是，也可以随机地从多个匹配度中选取至少一个目标匹配度，或者是按照本领域技术人员容易想到的其他规则选取至少一个目标匹配度，本实施例不做具体限定。
在一实施例中，预设匹配度根据三维模型的构建进度确定，构建进度可以根据三维数据流的接收进度确定，由于能够实时地根据获取的三维数据流构建目标对象的三维模型，因此构建进度与三维数据流的接收进度之间的误差较小。需要说明的是，三维模型的构建进度越大，预设匹配度也随之越大，三维模型的构建进度变小，预设匹配度也随之变小。接收进度、构建进度以及预设匹配度之间的关系可以由用户自行设置，可选的，通过映射关系表进行设置。例如，三维数据流的接收进度为30％时，通过映射关系表确定三维模型的构建进度为25％，预设匹配度为20％。
子步骤S1022、将至少一个目标匹配度对应的预设三维模型确定为与三维模型匹配的预设三维模型。
匹配度与预设三维模型相对应，目标匹配度同样与预设三维模型相对应，将至少一个目标匹配度对应的预设三维模型确定为与三维模型匹配的预设三维模型，即建立目标对象的三维模型与至少一个预设三维模型之间的匹配关系，以便后续调用至少一个预设三维模型来更新目标对象的三维模型，无需费时费力地生成完整的三维模型，提高目标对象的三维模型的成像效率。
在一实施例中，对多个匹配度进行排序，并按照排序顺序选取至少一个目标匹配度；通过显示装置显示至少一个目标匹配度对应的预设三维模型；基于用户对显示的至少一个预设三维模型的触发操作，从至少一个预设三维模型中确定与三维模型匹配的预设三维模型。需要说明的是，排序顺序可以是从大到小的顺序，便于用户自行选取预设三维模型与三维模型进行匹配，加快了三维模型的成像过程。
步骤S103、根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。
利用与三维模型匹配的预设三维模型将目标对象的三维模型替换，从而得到目标对象的目标三维模型，将未构建完成的三维模型更新为构建完成的预设三维模型，无需费时费 力地生成完整的三维模型，能够实时且快速地生成目标对象的目标三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
在一实施例中，XR设备包括显示装置，该显示装置例如为多面屏、智能眼镜、智能头盔等。通过显示装置显示与三维模型匹配的预设三维模型，并根据接收的用户触发的确认指令选取预设三维模型，以及确定是否根据与三维模型匹配的预设三维模型，更新三维模型，从而得到目标对象的目标三维模型。
在一实施例中，显示目标三维模型；根据用户触发的编辑指令，对显示的目标三维模型进行编辑。其中，XR设备包括显示装置和控制装置，控制装置包括手持交互设备，例如为摇杆、遥控器、终端等。需要说明的是，通过显示装置显示目标三维模型，控制装置用于对显示的目标三维模型进行编辑，基于用户对控制装置的触发操作，生成编辑指令，根据用户触发的编辑指令，对显示的目标三维模型进行编辑。能够实现对目标三维模型的编辑，无需用户切换设备来编辑三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
在一实施例中，编辑指令包括模型调整指令。根据用户触发的模型调整指令，确定显示的目标三维模型的位置、色彩、纹理、尺寸和/或形状的模型调整参数；根据模型调整参数，对显示的目标三维模型进行调整。需要说明的是，用户可以通过控制装置触发模型调整指令，从而调整目标三维模型的位置、色彩、纹理、尺寸和/或形状等，XR设备基于模型调整指令生成模型调整参数，并按照模型调整参数对显示的目标三维模型进行调整，操作简单易懂，不同于通过平面显示屏来编辑三维模型，通过XR设备来编辑三维模型能够提高虚拟世界的沉浸感，从而提高用户的编辑体验。
在一实施例中，编辑指令包括模型组合指令。根据用户触发的模型组合指令，选取至少一个预设三维模型，并确定至少一个预设三维模型对应的模型组合参数；根据模型组合参数，将至少一个预设三维模型与显示的目标三维模型进行组合。其中，数据库中存储有多个预设三维模型。需要说明的是，用户可以通过控制装置触发模型组合指令，从而从数据库中选取至少一个预设三维模型，并确定如何将选取的预设三维模型与目标三维模型进行组合，组合过程的操作简单，能够在虚拟世界中以搭积木式的方式，快速的构建出接近真实效果的虚拟场景，不同于通过平面显示屏来编辑三维模型，通过XR设备进行模型组合能够最大程度的还原用户在虚拟世界的沉浸感，从而提高用户体验。
在一实施例中，得到目标对象的目标三维模型之后，将目标三维模型作为预设三维模型添加至多个预设三维模型中。例如，将目标三维模型存储至存储有数据库的指定文件中，该指定文件存储有多个预设三维模型，从而扩大数据库中的预设三维模型的数量，便于预 设三维模型的匹配和调用。
请参照图3，图3为实施本公开实施例提供的三维模型生成方法的一场景示意图。如图3所示，三维扫描装置20对目标对象10进行扫描，得到目标对象10的三维数据。三维扫描装置20将采集到的目标对象10的三维数据汇集成三维数据流发送至XR设备30。XR设备30接收三维扫描装置20发送的目标对象10的三维数据流，并根据三维数据流构建目标对象10的三维模型，XR设备30计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型，根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象10的目标三维模型。
上述三维模型生成方法中，通过获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型，计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型，根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。实现了将XR技术与模型成像相结合，通过预设三维模型能够实时且快速地匹配到目标对象的目标三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
请参照图4，图4为本公开实施例提供的另一种三维模型生成方法的步骤流程示意图。
如图4所示，该三维模型生成方法包括步骤S201至S206。
步骤S201、获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型。
目标对象可以为物体、人体、环境等。例如，目标对象可以为车辆、沙发、房间等，可根据实际情况进行设定。三维数据流包括不间断发送的三维数据，XR设备能够实时地根据不间断发送的三维数据构建目标对象的三维模型，即该目标对象的三维模型随着三维数据流的堆叠而处于不断完善的过程中。
需要说明的是，本实施例所指的三维模型包括构建不完整的三维模型，例如包括构建进度为50％的三维模型，通过构建不完整的三维模型能够实现模型快速匹配，从而提高构建完整的三维模型的快速成像，优化了三维模型的成像过程。
三维扫描装置包括三维扫描仪、航拍无人机、探测雷达、超景深相机等设备，三维扫描装置与XR设备通信连接，例如通过5G网络连接，能够实时且快速进行三维数据的传输。通过三维扫描装置对目标对象进行扫描，并实时地将扫描得到的目标对象的三维数据流发送至XR设备，XR设备可以获取三维扫描装置实时采集到的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型。通过三维扫描装置与XR设备之间的实时通信， 实时且快速地生成目标对象的三维模型，有利于提高三维模型的开发效率。
步骤S202、计算三维模型与多个预设三维模型之间的匹配度。
XR设备中预存有多个预设三维模型，该预设三维模型为构建完整的三维模型，当然也可以为构建不完整的三维模型。计算目标对象的三维模型与多个预设三维模型之间的匹配度，得到与每个预设三维模型各自对应的匹配度。
步骤S203、若多个匹配度均小于预设匹配度，则继续获取三维扫描装置在扫描过程中发送的目标对象的三维数据流。
若多个匹配度均小于预设匹配度，即多个匹配度不包括大于或等于预设匹配度的目标匹配度，则认为多个预设三维模型不能与三维模型相匹配，此时继续获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，从而继续构建不完整的三维模型。例如，构建进度为25％的三维模型与多个预设三维模型之间的匹配度均小于预设匹配度，则继续获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，以继续生成构建进度为25％以上(例如构建进度为30％)的三维模型。
步骤S204、根据继续获取到的三维数据流，更新三维模型。
根据继续获取到的三维数据流，更新三维模型，从而得到构建进度更高的三维模型，构建进度高的三维模型更加完善，有利于后续计算三维模型与多个预设三维模型之间的匹配度，从而得到相匹配的预设三维模型。
在一实施例中，根据继续获取到的三维数据流更新三维模型之后，确定更新的三维模型的构建进度，当构建进度大于或等于预设构建进度时，将更新的三维模型确认为目标对象的目标三维模型；或者，接收用户触发的确认指令，并基于确认指令将更新的三维模型确认为目标对象的目标三维模型。其中，构建进度可以根据三维数据流的接收进度确定，构建进度与三维数据流的接收进度之间的误差较小，当构建进度大于或等于预设构建进度时，将更新的三维模型确认为目标对象的目标三维模型。例如，预设构建进度为99％，当构建进度大于或等于99％，认为该更新的三维模型为完整的三维模型，将该完整的三维模型作为目标对象的目标三维模型，无需进行后续的预设三维模型的匹配。或者，当用户认为更新的三维模型达到标准时，用户通过控制装置等触发确认指令，XR设备接收用户触发的确认指令，并基于确认指令将更新的三维模型确认为目标对象的目标三维模型。
在一实施例中，对更新的三维模型进行修正，得到目标对象的目标三维模型；将目标三维模型作为预设三维模型添加至多个预设三维模型中。例如，获取更新的三维模型的形状信息和多个点阵的坐标信息，根据形状信息和多个点阵的坐标信息确定异常点阵，调整 每个异常点阵的坐标信息，得到目标对象的目标三维模型。需要说明的是，根据形状信息和多个点阵的坐标信息可以确定三维模型的目标坐标信息，将目标坐标信息与多个点阵的坐标信息进行对比从而确定异常点阵，将异常点阵的坐标信息调整为对应的目标坐标信息，即可得到目标对象的目标三维模型。通过模型修正能够对更新的三维模型进行修正，提高目标三维模型的完整性。将目标三维模型作为预设三维模型添加至多个预设三维模型中，便于预设三维模型的匹配和调用。
在一实施例中，XR设备包括图形处理装置，通过图形处理装置对更新的三维模型进行修正。图形处理装置包括图形编辑模块和图形处理模块。图形编辑模块可适应模型编辑参数，可根据模型编辑参数编辑三维模型的位置、色彩、纹理、尺寸和/或形状的模型调整参数，或者根据模型组合参数将至少一个预设三维模型与显示的目标三维模型进行组合。通过图形处理模块可以主动或者被动地修正三维模型。
步骤S205、计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型。
更新三维模型之后，继续计算目标对象的三维模型与多个预设三维模型之间的匹配度，得到与每个预设三维模型各自对应的匹配度。三维模型经过更新之后变得更加完整，三维模型的构建进度更高，有利于通过多个匹配度确定与三维模型匹配的预设三维模型。
在一实施例中，数据库存储有多个预设三维模型，将三维模型发送至数据库，以将该三维模型与数据库存储的每个预设三维模型进行对比，得到多个匹配度，该匹配度与预设三维模型相对应。
步骤S206、根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。
利用与三维模型匹配的预设三维模型将目标对象的三维模型替换，从而得到目标对象的目标三维模型，将未构建完成的三维模型更新为构建完成的预设三维模型，无需费时费力地生成完整的三维模型，能够智能且快速地生成目标对象的目标三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
上述三维模型生成方法中，通过获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型，计算三维模型与多个预设三维模型之间的匹配度，若多个匹配度均小于预设匹配度，则继续获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，根据继续获取到的三维数据流，更新三维模型，计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型，根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三 维模型。实现了将XR技术与模型成像相结合，通过预设三维模型能够实时且快速地匹配到目标对象的目标三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
请参阅图5，图5为本公开实施例提供的一种XR设备的结构示意性框图。该XR扩展现实设备包括VR设备、AR设备、MR设备和/或穿戴式设备等。例如，XR设备为HoloSuit(世界上第一款实现了无线双向反馈的全身动捕XR设备)，该XR设备包括一件体感衣、一双手套以及一条运动裤。
如图5所示，XR设备300包括处理器301和存储器302，处理器301和存储器302通过总线303连接，该总线比如为I2C(Inter-integrated Circuit)总线。
例如，处理器301用于提供计算和控制能力，支撑整个XR设备的运行。处理器301可以是中央处理单元(Central Processing Unit，CPU)，该处理器301还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中，通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
例如，存储器302可以是Flash芯片、只读存储器(ROM，Read-Only Memory)磁盘、光盘、U盘或移动硬盘等。
本领域技术人员可以理解，图5中示出的结构，仅仅是与本公开实施例相关的部分结构的框图，并不构成对本公开实施例所应用于其上的XR设备的限定，具体的XR设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
处理器配置为运行存储在存储器中的计算机程序，并在执行计算机程序时实现本公开实施例提供的任意一种所述的三维模型生成方法。
在一实施例中，处理器配置为运行存储在存储器中的计算机程序，并在执行计算机程序时实现如下步骤：获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型；计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型；根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。
在一实施例中，处理器在实现根据多个匹配度确定与三维模型匹配的预设三维模型时，还配置为实现如下步骤：从多个匹配度中选取至少一个目标匹配度；将至少一个目标匹配度对应的预设三维模型确定为与三维模型匹配的预设三维模型。
在一实施例中，处理器在实现从多个匹配度中选取至少一个目标匹配度时，还配置为实现如下步骤：对多个匹配度进行排序，并按照排序顺序选取至少一个目标匹配度；和/或从多个匹配度中选取大于或等于预设匹配度的至少一个目标匹配度。
在一实施例中，处理器在实现计算三维模型与多个预设三维模型之间的匹配度之后，还配置为实现如下步骤：若多个匹配度均小于预设匹配度，则继续获取三维扫描装置在扫描过程中发送的目标对象的三维数据流；根据继续获取到的三维数据流，更新三维模型；执行计算三维模型与多个预设三维模型之间的匹配度的步骤。
在一实施例中，处理器在实现根据继续获取到的三维数据流，更新三维模型之后，还配置为实现如下步骤：确定更新的三维模型的构建进度，当构建进度大于或等于预设构建进度时，将更新的三维模型确认为目标对象的目标三维模型；或者接收用户触发的确认指令，并基于确认指令将更新的三维模型确认为目标对象的目标三维模型。
在一实施例中，处理器在实现根据继续获取到的三维数据流，更新三维模型之后，还配置为实现如下步骤：对更新的三维模型进行修正，得到目标对象的目标三维模型；将目标三维模型作为预设三维模型添加至多个预设三维模型中。
在一实施例中，处理器还配置为实现如下步骤：显示目标三维模型；根据用户触发的编辑指令，对显示的目标三维模型进行编辑。
在一实施例中，处理器在实现根据用户触发的编辑指令，对显示的目标三维模型进行编辑时，还配置为实现如下步骤：根据用户触发的模型调整指令，确定显示的目标三维模型的位置、色彩、纹理、尺寸和/或形状的模型调整参数；根据模型调整参数，对显示的目标三维模型进行调整；或者根据用户触发的模型组合指令，选取至少一个预设三维模型，并确定至少一个预设三维模型对应的模型组合参数；根据模型组合参数，将至少一个预设三维模型与显示的目标三维模型进行组合。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的XR设备的具体工作过程，可以参考前述三维模型生成方法实施例中的对应过程，在此不再赘述。
本公开实施例还提供一种存储介质，用于计算机可读存储，该存储介质存储有一个或者多个程序，一个或者多个程序可被一个或者多个处理器执行，以实现如本公开提供的任一项三维模型生成方法的步骤。
所述存储介质可以是前述实施例所述的XR设备的内部存储单元，例如所述XR设备的硬盘或内存。所述存储介质也可以是所述XR设备的外部存储设备，例如所述XR设备 上配备的插接式硬盘、智能存储卡(Smart Media Card，SMC)、安全数字(Secure Digital，SD)卡、闪存卡(Flash Card)等。
利用本公开提供的三维模型生成方法、XR设备及存储介质，通过获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据三维数据流构建目标对象的三维模型，然后计算三维模型与多个预设三维模型之间的匹配度，并根据多个匹配度确定与三维模型匹配的预设三维模型，再根据与三维模型匹配的预设三维模型，更新三维模型，得到目标对象的目标三维模型。本公开将XR技术与模型成像相结合，无需费时费力地生成完整的三维模型，通过预设三维模型能够实时且快速地匹配到目标对象的目标三维模型，优化了现有的三维模型的成像过程，大大提高了三维场景的开发效率。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施方式中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。
应当理解，在本公开说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本公开实施例序号仅仅为了描述，不代表实施例的优劣。以上所述，仅为本公开的具体实施方式，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种三维模型生成方法，应用于扩展现实XR设备，包括：
    获取三维扫描装置在扫描过程中发送的目标对象的三维数据流，并根据所述三维数据流构建所述目标对象的三维模型；
    计算所述三维模型与多个预设三维模型之间的匹配度，并根据多个所述匹配度确定与所述三维模型匹配的预设三维模型；
    根据与所述三维模型匹配的预设三维模型，更新所述三维模型，得到所述目标对象的目标三维模型。
  2. 根据权利要求1所述的三维模型生成方法，其中，所述根据多个所述匹配度确定与所述三维模型匹配的预设三维模型，包括：
    从多个所述匹配度中选取至少一个目标匹配度；
    将至少一个所述目标匹配度对应的预设三维模型确定为与所述三维模型匹配的预设三维模型。
  3. 根据权利要求2所述的三维模型生成方法，其中，所述从多个所述匹配度中选取至少一个目标匹配度，包括：
    对多个所述匹配度进行排序，并按照排序顺序选取至少一个目标匹配度；和/或
    从多个所述匹配度中选取大于或等于预设匹配度的至少一个目标匹配度。
  4. 根据权利要求1所述的三维模型生成方法，其中，所述计算所述三维模型与多个预设三维模型之间的匹配度之后，还包括：
    若多个所述匹配度均小于预设匹配度，则继续获取所述三维扫描装置在扫描过程中发送的目标对象的三维数据流；
    根据继续获取到的三维数据流，更新所述三维模型；
    执行所述计算所述三维模型与多个预设三维模型之间的匹配度的步骤。
  5. 根据权利要求4所述的三维模型生成方法，其中，所述根据继续获取到的三维数据流，更新所述三维模型之后，还包括：
    确定更新的所述三维模型的构建进度，当所述构建进度大于或等于预设构建进度时，将更新的所述三维模型确认为所述目标对象的目标三维模型；或者
    接收用户触发的确认指令，并基于所述确认指令将更新的所述三维模型确认为所 述目标对象的目标三维模型。
  6. 根据权利要求4所述的三维模型生成方法，其中，所述根据继续获取到的三维数据流，更新所述三维模型之后，还包括：
    对更新的所述三维模型进行修正，得到所述目标对象的目标三维模型；
    将所述目标三维模型作为预设三维模型添加至所述多个预设三维模型中。
  7. 根据权利要求1-6中任一项所述的三维模型生成方法，其中，所述方法还包括：
    显示所述目标三维模型；
    根据用户触发的编辑指令，对显示的所述目标三维模型进行编辑。
  8. 根据权利要求7所述的三维模型生成方法，其中，所述根据用户触发的编辑指令，对显示的所述目标三维模型进行编辑，包括：
    根据用户触发的模型调整指令，确定显示的所述目标三维模型的位置、色彩、纹理、尺寸和/或形状的模型调整参数；
    根据所述模型调整参数，对显示的所述目标三维模型进行调整；或者
    根据用户触发的模型组合指令，选取至少一个预设三维模型，并确定至少一个所述预设三维模型对应的模型组合参数；
    根据所述模型组合参数，将至少一个所述预设三维模型与显示的所述目标三维模型进行组合。
  9. 一种XR设备，其中，所述XR设备包括处理器、存储器、存储在所述存储器上并可被所述处理器执行的计算机程序以及用于实现所述处理器和所述存储器之间的连接通信的数据总线，其中，所述计算机程序被所述处理器执行时，实现如权利要求1至8中任一项所述的三维模型生成方法的步骤。
  10. 一种存储介质，用于计算机可读存储，其中，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现权利要求1至8中任一项所述的三维模型生成方法的步骤。
PCT/CN2021/133183 2020-12-28 2021-11-25 三维模型生成方法、xr设备及存储介质 WO2022142908A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011584771.1 2020-12-28
CN202011584771.1A CN114758055A (zh) 2020-12-28 2020-12-28 三维模型生成方法、xr设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022142908A1 true WO2022142908A1 (zh) 2022-07-07

Family

ID=82260193

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/133183 WO2022142908A1 (zh) 2020-12-28 2021-11-25 三维模型生成方法、xr设备及存储介质

Country Status (2)

Country Link
CN (1) CN114758055A (zh)
WO (1) WO2022142908A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115457202A (zh) * 2022-09-07 2022-12-09 北京四维远见信息技术有限公司 一种三维模型更新的方法、装置及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116704156B (zh) * 2023-04-28 2024-07-02 北京优酷科技有限公司 模型生成方法、电子设备及模型生成系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913492A (zh) * 2016-04-06 2016-08-31 浙江大学 一种rgbd图像中物体形状的补全方法
CN109685907A (zh) * 2017-10-18 2019-04-26 深圳市掌网科技股份有限公司 基于增强现实的图像结合方法及系统
US20190251744A1 (en) * 2018-02-12 2019-08-15 Express Search, Inc. System and method for searching 3d models using 2d images
CN111179408A (zh) * 2018-11-12 2020-05-19 北京物语科技有限公司 三维建模的方法及设备
CN113436350A (zh) * 2021-07-07 2021-09-24 武汉湾流科技股份有限公司 一种三维模型生成方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913492A (zh) * 2016-04-06 2016-08-31 浙江大学 一种rgbd图像中物体形状的补全方法
CN109685907A (zh) * 2017-10-18 2019-04-26 深圳市掌网科技股份有限公司 基于增强现实的图像结合方法及系统
US20190251744A1 (en) * 2018-02-12 2019-08-15 Express Search, Inc. System and method for searching 3d models using 2d images
CN111179408A (zh) * 2018-11-12 2020-05-19 北京物语科技有限公司 三维建模的方法及设备
CN113436350A (zh) * 2021-07-07 2021-09-24 武汉湾流科技股份有限公司 一种三维模型生成方法及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115457202A (zh) * 2022-09-07 2022-12-09 北京四维远见信息技术有限公司 一种三维模型更新的方法、装置及存储介质

Also Published As

Publication number Publication date
CN114758055A (zh) 2022-07-15

Similar Documents

Publication Publication Date Title
CN108335353B (zh) 动态场景的三维重建方法、装置和系统、服务器、介质
KR102125293B1 (ko) 생성 장치, 생성 방법, 및 기억 매체
CN108286945B (zh) 基于视觉反馈的三维扫描系统和方法
US20140218354A1 (en) View image providing device and method using omnidirectional image and 3-dimensional data
TWI534755B (zh) 三維立體模型之建立方法和裝置
TW201915944A (zh) 圖像處理方法、裝置、系統和儲存介質
WO2022142908A1 (zh) 三维模型生成方法、xr设备及存储介质
US10403001B2 (en) Producing three-dimensional representation based on images of an object
US10169891B2 (en) Producing three-dimensional representation based on images of a person
US10147240B2 (en) Product image processing method, and apparatus and system thereof
CN112270736A (zh) 增强现实处理方法及装置、存储介质和电子设备
US10163250B2 (en) Arbitrary view generation
CN113724391A (zh) 三维模型构建方法、装置、电子设备和计算机可读介质
JP2019103126A (ja) カメラシステム、カメラ制御装置、カメラ制御方法及びプログラム
JP7040511B2 (ja) 情報処理装置および方法
JP2019114269A (ja) 仮想視点画像を生成するシステム、方法及びプログラム
CN114821791A (zh) 一种图像三维动作信息的捕捉方法和系统
JP7366563B2 (ja) 画像生成装置、画像生成方法、及びプログラム
CN114241127A (zh) 全景图像生成方法、装置、电子设备和介质
KR102146839B1 (ko) 실시간 가상현실 구축을 위한 시스템 및 방법
JP2017215706A (ja) 映像合成方法、映像取得装置、映像合成装置、映像合成システム及びコンピュータプログラム。
WO2021166751A1 (ja) 情報処理装置、情報処理方法及びコンピュータプログラム
WO2023199583A1 (ja) ビューワ制御方法及び情報処理装置
WO2024181137A1 (ja) 情報処理装置および方法
JP2022114626A (ja) 情報処理装置、情報処理方法、およびプログラム

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: 21913650

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16.11.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21913650

Country of ref document: EP

Kind code of ref document: A1