WO2023108992A1 - 图像处理方法、装置、存储介质、电子设备和程序产品 - Google Patents
图像处理方法、装置、存储介质、电子设备和程序产品 Download PDFInfo
- Publication number
- WO2023108992A1 WO2023108992A1 PCT/CN2022/090722 CN2022090722W WO2023108992A1 WO 2023108992 A1 WO2023108992 A1 WO 2023108992A1 CN 2022090722 W CN2022090722 W CN 2022090722W WO 2023108992 A1 WO2023108992 A1 WO 2023108992A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- preset
- target
- brightness
- image
- channel
- Prior art date
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000005540 biological transmission Effects 0.000 claims description 46
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005286 illumination Methods 0.000 abstract description 5
- 238000002834 transmittance Methods 0.000 abstract 2
- 238000012549 training Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 239000000463 material Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000009877 rendering Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013256 Gubra-Amylin NASH model Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 240000007509 Phytolacca dioica Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Definitions
- the present disclosure relates to the field of computer technology, and in particular, to an image processing method, device, storage medium, electronic equipment and program product.
- shadow removal processing has received more and more attention.
- the shadow removal process can be implemented by using a preset model, and the training of the preset model requires a large number of shadow images and non-shadow images corresponding to each other as training data.
- shadow images and non-shadow images can be obtained by manual shooting as training data, but the method of manual shooting to obtain shadow images is time-consuming, labor-intensive and inefficient.
- the present disclosure provides an image processing method, device, storage medium, electronic equipment and program product.
- an image processing method comprising:
- the light transmission information includes a target opacity of each pixel position of the image to be processed; performing shadow processing on the image to be processed according to a preset shadow attenuation parameter and the light transmission information, Obtaining the target shadow image corresponding to the image to be processed includes:
- the target reflection brightness is used to characterize the reflection brightness of the target object in the image to be processed under the preset lighting environment
- performing shadow processing on the image to be processed according to the target opacity and the target reflection brightness to obtain the target shadow image includes:
- the target shadow image is generated according to the target luminance at multiple pixel positions.
- the image to be processed includes multiple channels, the first brightness includes first channel brightness of multiple channels, and the target reflected brightness includes target channel reflected brightness of multiple channels; Processing the first brightness of each pixel position of the image, the target opacity and the target reflection brightness, and obtaining the target brightness of each pixel position includes:
- the target of the channel at the pixel position is calculated by the following formula Single channel brightness:
- XS k (1-m)*XN k +m*XD k ;
- XS k represents the target single-channel brightness of the k-th channel
- m represents the target opacity
- XN k represents the first channel brightness of the k-th channel
- XD k represents the target channel reflection brightness of the k-th channel
- the target single-channel luminance of multiple channels is combined to obtain the target luminance of the pixel position.
- the preset shadow attenuation parameters include a preset direct reflection brightness and a preset ambient light attenuation factor
- the preset direct reflection brightness is used to characterize the effect of the target object on direct lighting in the preset lighting environment.
- the reflected light brightness of the light source, the preset ambient light attenuation factor is used to characterize the attenuation factor of the ambient lighting light source under the preset lighting environment;
- the determination of the target reflected brightness of each pixel position according to the preset shadow attenuation parameters includes :
- the target reflection brightness of each pixel position is acquired.
- the preset direct reflection brightness includes a preset direct reflection channel brightness of each channel; according to the preset direct reflection brightness, the preset ambient light attenuation factor and the first brightness, the obtained
- the target reflection luminance for each pixel location consists of:
- the target channel reflection brightness of each channel at the pixel position is calculated by the following formula:
- XD k represents the target channel reflection brightness of the kth channel
- XN k represents the first channel brightness of the kth channel
- ⁇ k represents the preset direct reflection channel brightness of the kth channel
- ⁇ represents the Preset ambient light attenuation factor
- the target channel reflectance luminance of the multiple channels is used as the target reflectance luminance of the pixel position.
- the acquisition of light transmission information of the image to be processed under a preset lighting environment includes:
- the preset lighting environment includes a preset light source, a preset occluder, a preset camera, and a preset virtual plane;
- the model brightness of each pixel position in the preset virtual plane is captured by the preset camera;
- the light transmission information of the image to be processed under the preset lighting environment is determined.
- an image processing device comprising:
- An information acquisition module configured to acquire light transmission information of the image to be processed under a preset lighting environment
- the image processing module is configured to perform shadow processing on the image to be processed according to preset shadow attenuation parameters and the light transmission information to obtain a target shadow image corresponding to the image to be processed; wherein the preset shadow attenuation
- the parameter is used to characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment.
- the light transmission information includes the target opacity of each pixel position of the image to be processed; the image processing module is configured to determine the target reflection of each pixel position according to a preset shadow attenuation parameter Brightness, the target reflection brightness is used to characterize the reflection brightness of the target object in the image to be processed under the preset lighting environment; according to the target opacity and the target reflection brightness, the to-be-processed Perform shadow processing on the image to obtain the target shadow image.
- the image processing module is configured to acquire the target brightness of each pixel position according to the first brightness of each pixel position of the image to be processed, the target opacity and the target reflection brightness;
- the target shadow image is generated according to the target luminance at multiple pixel positions.
- the image to be processed includes multiple channels, the first brightness includes first channel brightness of multiple channels, and the target reflected brightness includes target channel reflected brightness of multiple channels; the image processing module, For each channel of each pixel position of the image to be processed, according to the first channel brightness, the target opacity and the target channel reflection brightness, the following formula is used to calculate the pixel position
- the target single-channel brightness of the channel: XS k (1-m)*XN k +m*XD k ; wherein, XS k represents the target single-channel brightness of the kth channel, m represents the target opacity, and XN k represents the target single-channel brightness
- the first channel luminance of the kth channel, XD k represents the target channel reflection luminance of the kth channel; the target single-channel luminance of multiple channels is combined to obtain the target luminance of the pixel position.
- the preset shadow attenuation parameters include a preset direct reflection brightness and a preset ambient light attenuation factor
- the preset direct reflection brightness is used to characterize the effect of the target object on direct lighting in the preset lighting environment.
- the reflected light brightness of the light source, the preset ambient light attenuation factor is used to characterize the attenuation factor of the ambient lighting light source in the preset lighting environment;
- the image processing module is configured to according to the preset direct reflection brightness, The preset ambient light attenuation factor and the first brightness obtain the target reflection brightness of each pixel position.
- the preset direct reflection brightness includes a preset direct reflection channel brightness of each channel; the image processing module is configured to, for each pixel position, according to the preset direct reflection channel brightness, the The ambient light attenuation factor and the brightness of the first channel are preset, and the reflection brightness of the target channel of each channel at the pixel position is calculated by the following formula: Wherein, XD k represents the target channel reflection brightness of the kth channel, XN k represents the first channel brightness of the kth channel of the image to be processed, and ⁇ k represents the preset direct reflection channel brightness of the kth channel, ⁇ represents the preset ambient light attenuation factor; the target channel reflection brightness of multiple channels is used as the target reflection brightness of the pixel position.
- the information acquisition module is configured to determine a preset lighting environment, and the preset lighting environment includes a preset light source, a preset occluder, a preset camera, and a preset virtual plane;
- the model brightness of each pixel position in the preset virtual plane is captured by the preset camera; according to the preset virtual plane and the model brightness, it is determined that the image to be processed is Light transmission information in the environment.
- an electronic device including:
- memory for storing processor-executable instructions
- the processor is configured to execute the steps of the image processing method provided in the first aspect of the present disclosure.
- a computer-readable storage medium on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the image processing method provided in the first aspect of the present disclosure are implemented.
- a computer program product includes a computer program executable by a programmable device, and the computer program has a function for executing the present invention when executed by the programmable device.
- the code part of the steps of the image processing method provided by the first aspect is disclosed.
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: acquire the light transmission information of the image to be processed under the preset lighting environment; perform shadow processing on the image to be processed according to the preset shadow attenuation parameters and the light transmission information , to obtain the target shadow image corresponding to the image to be processed; wherein, the preset shadow attenuation parameter is used to characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment. Since the above-mentioned preset shadow attenuation parameters can characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment, a target shadow image matching the actual preset lighting environment can be obtained, and since manual shooting is not required, The efficiency of shadow image acquisition can be improved.
- Fig. 1 is a flowchart of an image processing method according to an exemplary embodiment.
- Fig. 2 is a flow chart showing a step of S102 according to the embodiment shown in Fig. 1 .
- Fig. 3 is a flow chart of step S101 according to the embodiment shown in Fig. 1 .
- Fig. 4 is a schematic diagram showing a preset lighting environment according to an exemplary embodiment.
- Fig. 5 is a block diagram of an image processing device according to an exemplary embodiment.
- Fig. 6 is a block diagram of an electronic device according to an exemplary embodiment.
- the present disclosure can be applied to image processing scenarios, especially the scenario of performing shadow processing on images.
- image processing scenarios especially the scenario of performing shadow processing on images.
- a large number of corresponding shadow images and non-shadow images are required as training data.
- shadow images and non-shadow images may be obtained as training data by manual shooting, which is time-consuming, labor-intensive and inefficient.
- shadow processing of images can also be done in the following ways:
- the image is shaded by GAN (Generative Adversarial Networks, Generative Adversarial Networks).
- GAN Geneative Adversarial Networks, Generative Adversarial Networks. This method needs to obtain training samples, and obtain the GAN model after training according to the training samples. However, the acquisition cost of training samples is high and the efficiency is low, and fewer training samples can be obtained, resulting in lower accuracy of the generated GAN model. Less variety of shades.
- Shadows an unshaded image For example, in a virtual reality scene, the shadow effect after the target object is blocked by buildings or trees also needs to perform shadow processing on the image corresponding to the target object.
- the present disclosure provides an image processing method, device, storage medium, electronic equipment, and program product.
- Fig. 1 is an image processing method shown according to an exemplary embodiment.
- the execution subject of the method may be a terminal, and the method may include:
- the light transmission information may be used to characterize the transparency or opacity of the image to be processed under a preset lighting environment.
- the image to be processed may be an unshaded image.
- the preset shadow attenuation parameter is used to characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment.
- the target object may be a target object, a target animal, a target plant, or a target person, etc., which is not limited in the present disclosure.
- the material, color, shape, etc. of the target object will affect the reflection coefficient, therefore, the preset shadow attenuation parameter can be determined according to the material, color, shape, etc. of the target object.
- the preset shadow attenuation parameter may include a plurality of different parameter values for representing different reflection coefficients of target objects of different materials, colors or shapes under the preset lighting environment.
- each preset lighting environment can also be one or more, and each preset lighting environment corresponds to a piece of light transmission information, and each preset lighting environment can also correspond to multiple preset shadow attenuation factors.
- each preset lighting environment can also correspond to multiple preset shadow attenuation factors.
- the above light transmission information may include the target opacity of each pixel position of the image to be processed.
- the target opacity of each pixel position can be used to characterize the intensity of the occluded light at the pixel position. If the pixel position is in the umbra, the pixel position is completely occluded, and the shadow intensity is the largest, and the pixel position can be determined The corresponding target opacity is 1; if the pixel position is in the penumbra, the light at the pixel position is partially blocked, and the shadow intensity is between the minimum value and the maximum value, and the target corresponding to the pixel position can be determined according to the shadow intensity Opacity is a value greater than 0 and less than 1; if the pixel position is not blocked by shadows, the shadow intensity at this pixel position is the smallest, and it can be determined that the target opacity corresponding to this pixel position is 0.
- Fig. 2 is a flowchart of a step S102 according to the embodiment shown in Fig. 1, as shown in Fig. 2, the step S102 above may include the following steps:
- the target reflection brightness is used to characterize the reflection brightness of the target object in the image to be processed under the preset lighting environment.
- the corresponding preset shadow attenuation parameters may be determined according to the material of the target object, so as to determine the reflected brightness corresponding to the material of the target object.
- the image to be processed may include a plurality of pixels, and the target luminance of each pixel position may be obtained first; then, a target shadow image is generated according to the target luminance of the plurality of pixel positions.
- the brightness of each pixel position of the image to be processed may be adjusted to the target brightness, so as to form a shadow effect and obtain a target shadow image.
- the manner of acquiring the target brightness of each pixel position may include: acquiring the target brightness of each pixel position according to the first brightness of each pixel position of the image to be processed, the target opacity and the target reflection brightness.
- an image may include three channels of red, green, and blue
- the above-mentioned first brightness may include the first channel brightness of each channel of red, green, and blue.
- the three channels of red, green, and blue at a pixel position correspond to The brightness of the first channel of can also be synthesized into the first brightness of the pixel position. Therefore, the target single-channel luminance of each channel at each pixel position can be calculated first, and then the target single-channel luminance of the red, green and blue channels can be combined and calculated to obtain the target luminance of the pixel position.
- the image to be processed includes multiple channels, the first brightness includes first channel brightness of multiple channels, and the target reflected brightness includes target channel reflected brightness of multiple channels; each pixel of the image to be processed can be Each channel of the position, according to the brightness of the first channel, the opacity of the target and the reflection brightness of the target channel, calculate the target single-channel brightness of the channel at the pixel position by the following formula (1):
- XS k represents the target single-channel brightness of the k-th channel
- m represents the target opacity
- XN k represents the first-channel brightness of the k-th channel
- XD k represents the target channel reflection brightness of the k-th channel
- k is positive integer.
- the value ranges of the above-mentioned XS k , XN k , XD k and m may all be values greater than or equal to 0 and less than or equal to 1.
- the target single-channel luminance of multiple channels can be combined to obtain the target luminance of the pixel position.
- the target brightness of each pixel position of the image to be processed can be obtained, so as to complete the shadow processing of the image to be processed, so that the processed target shadow image can reflect the shadow effect more realistically.
- the above-mentioned target opacity can be multiple, and the above-mentioned preset shadow attenuation parameters can also be multiple, so that according to the random combination of multiple target opacities and multiple shadow attenuation parameters, multiple target shadow images can be obtained, so that A richer target shadow image is obtained, and the efficiency of shadow image acquisition is further improved.
- the above light transmission information may include a target transparency of each pixel position of the image to be processed.
- the target single channel of the channel at the pixel position can be calculated by the following formula (2) brightness:
- XS k represents the target single-channel brightness of the kth channel
- n represents the target transparency
- XN k represents the first channel brightness of the kth channel
- XD k represents the target channel reflection brightness of the kth channel
- k is a positive integer .
- the target single-channel luminance of multiple channels can also be combined to obtain the target luminance of the pixel position.
- the preset shadow attenuation parameters include a preset direct reflection brightness and a preset ambient light attenuation factor
- the preset direct reflection brightness is used to characterize the impact of the target object on the preset lighting environment.
- the reflected light brightness of the direct lighting source, the preset direct reflected brightness may include the preset direct reflected brightness of each channel, and the preset ambient light attenuation factor is used to represent the attenuation factor of the ambient lighting light source under the preset lighting environment.
- the preset lighting environment may include a preset light source and a preset occluder
- the preset light source may include a direct lighting source and an ambient lighting source; according to the position, material and shape of the above-mentioned target object, the target The reflected light brightness of the object to the direct illumination light source may be used as the above-mentioned preset direct reflected brightness.
- the attenuation factor of the preset occluder to the ambient lighting source can be determined, and the attenuation factor can be used as the preset ambient light attenuation factor.
- multiple preset direct reflection brightnesses can be determined.
- multiple preset ambient light attenuation factors can be obtained.
- the target reflection brightness of each pixel position may be acquired according to the preset direct reflection brightness, the preset ambient light attenuation factor and the first brightness.
- the preset direct reflection brightness may include a preset direct reflection channel brightness of each channel; for each pixel position, according to the preset direct reflection channel brightness, the preset ambient light attenuation factor and the above-mentioned first channel Brightness, the target channel reflection brightness of each channel at the pixel position is calculated by the following formula (3):
- XD k represents the target channel reflection brightness of the kth channel
- XN k represents the first channel brightness of the kth channel
- ⁇ k represents the preset direct reflection channel brightness of the kth channel
- ⁇ represents the preset ambient light Attenuation factor
- k is a positive integer.
- the target channel reflection luminance of multiple channels may be used as the target reflection luminance of the pixel position.
- the target reflection luminance closer to the target object can be obtained, so as to make the finally acquired target shadow image more realistic.
- Fig. 3 is a flowchart of a step S101 according to the embodiment shown in Fig. 1. As shown in Fig. 3, the above step S101 may include the following steps:
- the preset lighting environment may include a preset light source, a preset occluder, a preset camera, and a preset virtual plane.
- the preset lighting environment can be constructed by Blender (3D graphic image software), for example, in Blender, according to the preset shape, size and relative position information, place a preset light source, one or more A preset occluder, a preset camera, and a virtual plane can construct the preset lighting environment.
- Blender 3D graphic image software
- FIG. 4 is a schematic diagram showing a preset lighting environment according to an exemplary embodiment. As shown in FIG. and a preset virtual plane 404 .
- S1012 In the preset lighting environment, use a preset camera to capture the brightness of the model at each pixel position in the preset virtual plane.
- S1013. Determine light transmission information of the image to be processed under the preset lighting environment according to the preset virtual plane and the brightness of the model.
- the model brightness of each pixel position may be normalized to a value between 0 and 1, and the normalized value may be used as light transmission information of the pixel position. If the light transmission information includes the target opacity, then in the above normalization processing, the higher the model brightness is, the smaller the normalized value is; if the light transmission information includes the target transparency, then in the above normalization processing , the smaller the brightness of the model, the smaller the normalized value.
- different light transmission information can be obtained by performing random scaling, translation and rotation operations on the four components (preset light source, preset occluder, preset camera and preset virtual plane) in the preset lighting environment , so as to generate multiple target shadow images according to different light transmission information.
- the light transmission information may be stored in the form of a shadow mask.
- different light transmission information is stored through multiple different shadow masks, so as to obtain rich and diverse target shadow images.
- any method in the above-mentioned embodiments of the present disclosure is used to obtain the light transmission information of the image to be processed under the preset lighting environment; according to the preset shadow attenuation parameter and the light transmission information, the image to be processed is Shadow processing, obtaining a target shadow image corresponding to the image to be processed; wherein, the preset shadow attenuation parameter is used to characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment.
- the above-mentioned preset shadow attenuation parameters can characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment, a target shadow image matching the actual preset lighting environment can be obtained, and since manual shooting is not required, The efficiency of shadow image acquisition can be improved.
- Fig. 5 is a block diagram of an image processing device 500 according to an exemplary embodiment. As shown in Fig. 5, the device 500 may include:
- the information acquisition module 501 is configured to acquire light transmission information of the image to be processed under a preset lighting environment
- the image processing module 502 is configured to perform shadow processing on the image to be processed according to the preset shadow attenuation parameters and the light transmission information to obtain a target shadow image corresponding to the image to be processed; wherein the preset shadow attenuation parameters are used for Characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment.
- the light transmission information includes the target opacity of each pixel position of the image to be processed; the image processing module 502 is configured to determine the target reflection brightness of each pixel position according to a preset shadow attenuation parameter, the The target reflection brightness is used to characterize the reflection brightness of the target object in the image to be processed under the preset lighting environment; according to the target opacity and the target reflection brightness, the image to be processed is shaded to obtain the target shadow image.
- the image processing module 502 is configured to acquire the target brightness of each pixel position according to the first brightness of each pixel position of the image to be processed, the target opacity and the target reflection brightness; The target brightness at the pixel location from which the target shadow image is generated.
- the image to be processed includes multiple channels, the first brightness includes first channel brightness of multiple channels, and the target reflected brightness includes target channel reflected brightness of multiple channels;
- the preset shadow attenuation parameters include a preset direct reflection brightness and a preset ambient light attenuation factor
- the preset direct reflection brightness is used to characterize the reflected light of the target object to the direct lighting source in the preset lighting environment Brightness
- the preset ambient light attenuation factor is used to characterize the attenuation factor of the ambient lighting light source in the preset lighting environment
- the image processing module 502 is configured to and the first brightness to obtain the target reflection brightness of each pixel position.
- the preset direct reflection brightness includes a preset direct reflection channel brightness of each channel; the image processing module 502 is configured to, for each pixel position, according to the preset direct reflection channel brightness, the preset environment
- the light attenuation factor and the brightness of the first channel are calculated by the following formula to obtain the target channel reflection brightness of each channel at the pixel position:
- XD k represents the target channel reflection brightness of the kth channel
- XN k represents the first channel brightness of the kth channel
- ⁇ k represents the preset direct reflection channel brightness of the kth channel
- ⁇ represents the preset ambient light Attenuation factor
- k is a positive integer
- the target channel reflection brightness of multiple channels is used as the target reflection brightness of the pixel position.
- the information acquiring module 501 is configured to determine a preset lighting environment, which includes a preset light source, a preset occluder, a preset camera, and a preset virtual plane; in the preset lighting environment , using the preset camera to capture the model brightness of each pixel position in the preset virtual plane; according to the preset virtual plane and the model brightness, determine the light transmission information of the image to be processed under the preset lighting environment.
- the device in the above-mentioned embodiments of the present disclosure is used to obtain the light transmission information of the image to be processed under the preset lighting environment; according to the preset shadow attenuation parameter and the light transmission information, shadow processing is performed on the image to be processed , to obtain the target shadow image corresponding to the image to be processed; wherein, the preset shadow attenuation parameter is used to characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment.
- the above-mentioned preset shadow attenuation parameters can characterize the reflection coefficient of the target object in the image to be processed under the preset lighting environment, a target shadow image matching the actual preset lighting environment can be obtained, and since manual shooting is not required, The efficiency of shadow image acquisition can be improved.
- terminals in this disclosure may be electronic devices such as smart phones, tablet computers, smart watches, smart bracelets, PDA (Personal Digital Assistant, personal digital assistant), CPE (Customer Premise Equipment, customer terminal equipment) , which is not limited in the present disclosure.
- PDA Personal Digital Assistant, personal digital assistant
- CPE Customer Premise Equipment, customer terminal equipment
- the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of the image processing method provided in the present disclosure are implemented.
- Fig. 6 is a block diagram of an electronic device 600 according to an exemplary embodiment.
- the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, a router, and the like.
- electronic device 600 may include one or more of the following components: processing component 602, memory 604, power component 606, multimedia component 608, audio component 610, input/output (I/O) interface 612, sensor component 614, and communication component 616 .
- the processing component 602 generally controls the overall operations of the electronic device 600, such as those associated with display, telephone calls, data communications, camera operations, and recording operations.
- the processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above image processing method.
- processing component 602 may include one or more modules that facilitate interaction between processing component 602 and other components.
- processing component 602 may include a multimedia module to facilitate interaction between multimedia component 608 and processing component 602 .
- the memory 604 is configured to store various types of data to support operations at the electronic device 600 . Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phonebook data, messages, pictures, videos, and the like.
- the memory 604 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.
- SRAM static random access memory
- EEPROM electrically erasable programmable read-only memory
- EPROM erasable Programmable Read Only Memory
- PROM Programmable Read Only Memory
- ROM Read Only Memory
- Magnetic Memory Flash Memory
- Magnetic or Optical Disk Magnetic Disk
- the power component 606 provides power to various components of the electronic device 600 .
- Power components 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 600 .
- the multimedia component 608 includes a screen providing an output interface between the electronic device 600 and the user.
- the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user.
- the touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense a boundary of a touch or swipe action, but also detect a duration and pressure associated with the touch or swipe operation.
- the multimedia component 608 includes a front camera and/or a rear camera. When the electronic device 600 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capability.
- the audio component 610 is configured to output and/or input audio signals.
- the audio component 610 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 600 is in operation modes, such as call mode, recording mode and voice recognition mode. Received audio signals may be further stored in memory 604 or sent via communication component 616 .
- the audio component 610 also includes a speaker for outputting audio signals.
- the I/O interface 612 provides an interface between the processing component 602 and a peripheral interface module.
- the peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.
- Sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for electronic device 600 .
- the sensor assembly 614 can detect the open/close state of the electronic device 600, the relative positioning of the components, such as the display and the keypad of the electronic device 600, the sensor assembly 614 can also detect the electronic device 600 or one of the electronic device 600
- the position of components changes, the presence or absence of user contact with the electronic device 600 , the orientation or acceleration/deceleration of the electronic device 600 and the temperature of the electronic device 600 change.
- the sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact.
- Sensor assembly 614 may also include optical sensors, such as CMOS or CCD image sensors, for use in imaging applications.
- the sensor component 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
- the communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices.
- the electronic device 600 can access a wireless network based on a communication standard, such as Wi-Fi, 2G, 3G, 4G, 5G, NB-IOT, eMTC, or other 6G, etc., or a combination thereof.
- the communication component 616 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
- the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication.
- the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
- RFID Radio Frequency Identification
- IrDA Infrared Data Association
- UWB Ultra Wideband
- Bluetooth Bluetooth
- electronic device 600 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation for performing the image processing method described above.
- ASICs application specific integrated circuits
- DSPs digital signal processors
- DSPDs digital signal processing devices
- PLDs programmable logic devices
- FPGA field programmable A programmable gate array
- controller microcontroller, microprocessor or other electronic component implementation for performing the image processing method described above.
- non-transitory computer-readable storage medium including instructions, such as the memory 604 including instructions, which can be executed by the processor 620 of the electronic device 600 to implement the above image processing method.
- the non-transitory computer readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
- a computer program product comprising a computer program executable by a programmable device, the computer program having a function for performing the above-mentioned The code section for the steps of the image processing method.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
一种图像处理方法、装置、存储介质、电子设备和程序产品，方法包括：获取待处理图像在预设光照环境下的透光信息（S101）；根据预设阴影衰减参数和该透光信息，对待处理图像进行阴影处理，得到待处理图像对应的目标阴影图像（S102）；其中，预设阴影衰减参数用于表征待处理图像中的目标对象在预设光照环境下的反射系数。由于预设阴影衰减参数可以表征待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
Description
相关申请的交叉引用
本公开要求在2021年12月13日提交中国专利局、申请号为202111521335.4、名称为“图像处理方法、装置、存储介质及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
本公开涉及计算机技术领域，具体地，涉及一种图像处理方法、装置、存储介质、电子设备和程序产品。
随着计算机和互联网技术的不断发展，对图像进行去除阴影处理受到了越来越多的关注。去除阴影处理可以采用预设模型来实现，预设模型的训练需要大量相互对应的阴影图像与非阴影图像作为训练数据。在相关技术中，可以采用人工拍摄的方式来获取阴影图像与非阴影图像作为训练数据，但是人工拍摄获取阴影图像的方式耗时耗力，效率低下。
发明内容
为克服相关技术中存在的上述问题，本公开提供一种图像处理方法、装置、存储介质、电子设备和程序产品。
根据本公开实施例的第一方面，提供一种图像处理方法，所述方法包括：
获取待处理图像在预设光照环境下的透光信息；
根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像；其中，所述预设阴影衰减参数用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射系数。
可选地，所述透光信息包括所述待处理图像的每个像素位置的目标不透明度；所述根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像包括：
根据预设阴影衰减参数确定每个所述像素位置的目标反射亮度，所述目标反射亮度用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射光亮度；
根据所述目标不透明度和所述目标反射亮度，对所述待处理图像进行阴影处理，得到所述目标阴影图像。
可选地，所述根据所述目标不透明度和所述目标反射亮度，对所述待处理图像进行阴影处理，得到所述目标阴影图像包括：
根据所述待处理图像的每个像素位置的第一亮度、所述目标不透明度和所述目标反射亮度，获取每个像素位置的目标亮度；
根据多个像素位置的目标亮度，生成所述目标阴影图像。
可选地，所述待处理图像包括多个通道，所述第一亮度包括多个通道的第一通道亮度，所述目标反射亮度包括多个通道的目标通道反射亮度；所述根据所述待处理图像的每个像素位置的第一亮度、所述目标不透明度和所述目标反射亮度，获取每个像素位置的目标亮度包括：
针对所述待处理图像的每个像素位置的每个通道，根据所述第一通道亮度、所述目标不透明度和所述目标通道反射亮度，通过以下公式计算得到该像素位置的该通道的目标单通道亮度：
XS
k＝(1-m)*XN
k+m*XD
k；
其中，XS
k表示第k通道的目标单通道亮度，m表示所述目标不透明度，XN
k表示所述第k通道的第一通道亮度，XD
k表示所述第k通道的目标通道反射亮度；
将多个通道的目标单通道亮度合并得到该像素位置的目标亮度。
可选地，所述预设阴影衰减参数包括预设直接反射亮度和预设环境光衰减因子，所述预设直接反射亮度用于表征所述目标对象在所述预设光照环境下对直接照明光源的反射光亮度，所述预设环境光衰减因子用于表征环境照明光源在所述预设光照环境下的衰减因子；所述根据预设阴影衰减参数确定每个像素位置的目标反射亮度包括：
根据所述预设直接反射亮度、所述预设环境光衰减因子和所述第一亮度，获取每个像素位置的目标反射亮度。
可选地，所述预设直接反射亮度包括每个通道的预设直接反射通道亮度；所述根据所述预设直接反射亮度、所述预设环境光衰减因子和所述第一亮度，获取每个像素位置的目标反射亮度包括：
针对每个像素位置，根据所述预设直接反射通道亮度、所述预设环境光衰减因子和所述第一通道亮度，通过以下公式计算得到该像素位置的每个通道的目标通道反射亮度：
其中，XD
k表示所述第k通道的目标通道反射亮度，XN
k表示所述第k通道的第一通道亮度，α
k表示所述第k通道的预设直接反射通道亮度，γ表示所述预设环境光衰减因子；
将多个通道的目标通道反射亮度作为该像素位置的目标反射亮度。
可选地，所述获取待处理图像在预设光照环境下的透光信息包括：
确定预设光照环境，所述预设光照环境包括预设光源、预设遮挡物、预设相机和预设虚拟平面；
在所述预设光照环境中，通过所述预设相机捕获所述预设虚拟平面内每个像素位置的模型亮度；
根据所述预设虚拟平面和所述模型亮度，确定所述待处理图像在所述预设光照环境下的透光信息。
根据本公开实施例的第二方面，提供一种图像处理装置，所述装置包括：
信息获取模块，被配置为获取待处理图像在预设光照环境下的透光信息；
图像处理模块，被配置为根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像；其中，所述预设阴影衰减参数用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射系数。
可选地，所述透光信息包括所述待处理图像的每个像素位置的目标不透明度；所述图像处理模块，被配置为根据预设阴影衰减参数确定每个所述像素位置的目标反射亮度，所述目标反射亮度用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射光亮度；根据所述目标不透明度和所述目标反射亮度，对所述待处理图像进行阴影处理，得到所述目标阴影图像。
可选地，所述图像处理模块，被配置为根据所述待处理图像的每个像素位置的第一亮度、所述目标不透明度和所述目标反射亮度，获取每个像素位置的目标亮度；根据多个像素位置的目标亮度，生成所述目标阴影图像。
可选地，所述待处理图像包括多个通道，所述第一亮度包括多个通道的第一通道亮度，所述目标反射亮度包括多个通道的目标通道反射亮度；所述图像处理模块，被配置为针对所述待处理图像的每个像素位置的每个通道，根据所述第一通道亮度、所述目标不透明度和所述目标通道反射亮度，通过以下公式计算得到该像素位置的该通道的目标单通道亮度：XS
k＝(1-m)*XN
k+m*XD
k；其中，XS
k表示第k通道的目标单通道亮 度，m表示所述目标不透明度，XN
k表示所述第k通道的第一通道亮度，XD
k表示所述第k通道的目标通道反射亮度；将多个通道的目标单通道亮度合并得到该像素位置的目标亮度。
可选地，所述预设阴影衰减参数包括预设直接反射亮度和预设环境光衰减因子，所述预设直接反射亮度用于表征所述目标对象在所述预设光照环境下对直接照明光源的反射光亮度，所述预设环境光衰减因子用于表征环境照明光源在所述预设光照环境下的衰减因子；所述图像处理模块，被配置为根据所述预设直接反射亮度、所述预设环境光衰减因子和所述第一亮度，获取每个像素位置的目标反射亮度。
可选地，所述预设直接反射亮度包括每个通道的预设直接反射通道亮度；所述图像处理模块，被配置为针对每个像素位置，根据所述预设直接反射通道亮度、所述预设环境光衰减因子和所述第一通道亮度，通过以下公式计算得到该像素位置的每个通道的所述目标通道反射亮度：
其中，XD
k表示所述第k通道的目标通道反射亮度，XN
k表示所述待处理图像的第k通道的第一通道亮度，α
k表示所述第k通道的预设直接反射通道亮度，γ表示所述预设环境光衰减因子；将多个通道的目标通道反射亮度作为该像素位置的目标反射亮度。
可选地，所述信息获取模块，被配置为确定预设光照环境，所述预设光照环境包括预设光源、预设遮挡物、预设相机和预设虚拟平面；在所述预设光照环境中，通过所述预设相机捕获所述预设虚拟平面内每个像素位置的模型亮度；根据所述预设虚拟平面和所述模型亮度，确定所述待处理图像在所述预设光照环境下的透光信息。
根据本公开实施例的第三方面，提供一种电子设备，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器被配置为执行本公开第一方面所提供的图像处理方法的步骤。
根据本公开实施例的第四方面，提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开第一方面所提供的图像处理方法的步骤。
根据本公开实施例的第五方面，提供一种计算机程序产品，该计算机程序产品包含能够由可编程的装置执行的计算机程序，该计算机程序具有当由该可编程的装置执行时用于执行本公开第一方面所提供的图像处理方法的步骤的代码部分。
本公开的实施例提供的技术方案可以包括以下有益效果：获取待处理图像在预设光照环境下的透光信息；根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像；其中，该预设阴影衰减参数用于表征该待处理图像中的目标对象在该预设光照环境下的反射系数。由于上述预设阴影衰减参数可以表征该待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1是根据一示例性实施例示出的一种图像处理方法的流程图。
图2是根据图1所示实施例示出的一种S102步骤的流程图。
图3是根据图1所示实施例示出的一种S101步骤的流程图。
图4是根据一示例性实施例示出的一种预设光照环境的示意图。
图5是根据一示例性实施例示出的一种图像处理装置的框图。
图6是根据一示例性实施例示出的电子设备的框图。
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
首先，对本公开的应用场景进行说明。本公开可以应用于图像处理场景，特别是对图像进行阴影处理的场景。为了对去除阴影的预设模型进行训练，需要大量相互对应的阴影图像与非阴影图像作为训练数据。在相关技术中，可以采用人工拍摄的方式来获取阴影图像与非阴影图像作为训练数据，人工拍摄获取图像的方式耗时耗力，效率低下。除了人工拍摄，对图像进行阴影处理，还可以通过以下方式进行：
通过3D阴影渲染的方式对图像进行阴影处理：通过放置遮挡物并通过光线追踪在图像上渲染阴影。该方式渲染的结果可能在物理层面上不正确，但由于该方式无法根据图像中目标对象的材质信息对阴影渲染效果进行调整，因此会导致渲染的结果与实际的阴影图像有较大差异。
通过GAN(Generative Adversarial Networks，生成式对抗网络)对图像进行阴影处理。该方式需要获取训练样本，根据训练样本进行训练后得到GAN模型，但是，训练样本的获取成本高、效率低，能够获取训练样本较少，从而导致生成的GAN模型的准确性较低，提供的阴影种类较少。
可见，采用上述方式对图像进行阴影处理，无法提供准确的阴影图像。
需要说明的是，除了上述在对去除阴影的预设模型进行训练时需要大量的阴影图像外，在其他场景，例如虚拟现实等场景下，为了展示更加丰富和逼真的日常环境信息，通常也需要对无阴影图像进行阴影处理。例如在虚拟现实场景中目标对象被建筑物或树木遮挡后的阴影效果，也需要对目标对象对应的图像进行阴影处理。
为了解决上述问题，本公开提供了一种图像处理方法、装置、存储介质、电子设备和程序产品，可以根据待处理图像在预设光照环境下的透光信息和预设阴影衰减参数，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像，由于上述预设阴影衰减参数可以表征该待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
下面结合具体实施例对本公开进行说明。
图1是根据一示例性实施例示出的一种图像处理方法，如图1所示，该方法的执行主体可以是终端，该方法可以包括：
S101、获取待处理图像在预设光照环境下的透光信息。
其中，该透光信息可以用于表征该待处理图像在预设光照环境下的透明度或不透明度。该待处理图像可以是无阴影图像。
S102、根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像。
其中，该预设阴影衰减参数用于表征该待处理图像中的目标对象在该预设光照环境下的反射系数。
需要说明的是，该目标对象可以是目标物体、目标动物、目标植物或目标人物等，本公开对此不作限定。该目标对象的材质、颜色、形态等均会对反射系数造成影响，因此，该预设阴影衰减参数可以根据目标对象的材质、颜色和形态等确定该预设阴影衰减参数。另外，该预设阴影衰减参数可以包括多个不同的参数值，用于表征不同材质、颜色或形态的目标对象在该预设光照环境下的不同反射系数。
采用本公开上述实施例中的方法，获取待处理图像在预设光照环境下的透光信息；根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像；其中，该预设阴影衰减参数用于表征该待处理图像中的目标对象在该预设光照环境下的反射系数。由于上述预设阴影衰减参数可以表征该待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
进一步地，上述预设光照环境也可以为一个或多个，每个预设光照环境对应一个透光信息，每个预设光照环境还可以对应多个预设阴影衰减因子，这样，根据多个透光信息和多个预设阴影衰减因子的组合进行阴影处理，可以得到多样化且逼真的目标阴影图像。
在本公开的另一实施例中，上述透光信息可以包括待处理图像的每个像素位置的目标不透明度。
示例地，每个像素位置的目标不透明度可以用于表征该像素位置的光照被遮挡的强度，若像素位置处于本影内，则该像素位置被完全遮挡，阴影强度最大，可以确定该像素位置对应的目标不透明度为1；若像素位置处于半影内，则该像素位置的光照被遮挡了一部分，阴影强度处于最小值和最大值之间，可以根据该阴影强度确定该像素位置对应的目标不透明度为大于0且小于1的数值；若像素位置未被阴影遮挡，则该像素位置的阴影强度最小，可以确定该像素位置对应的目标不透明度为0。
图2是根据图1所示实施例示出的一种S102步骤的流程图，如图2所示，上述S102步骤可以包括以下步骤：
S1021、根据预设阴影衰减参数确定每个该像素位置的目标反射亮度。
其中，该目标反射亮度用于表征该待处理图像中的目标对象在该预设光照环境下的反射光亮度。
可选地，可以根据目标对象的材质确定对应的预设阴影衰减参数，从而确定与目标 对象的材质相对应的反射光亮度。
S1022、根据上述目标不透明度和目标反射亮度，对待处理图像进行阴影处理，得到目标阴影图像。
在本步骤，待处理图像可以包括多个像素，可以首先获取每个像素位置的目标亮度；然后根据多个像素位置的目标亮度，生成目标阴影图像。
示例地，可以将待处理图像的每个像素位置的亮度调整为该目标亮度，从而形成阴影效果，得到目标阴影图像。
获取每个像素位置的目标亮度的方式可以包括：根据该待处理图像的每个像素位置的第一亮度、该目标不透明度和该目标反射亮度，获取每个像素位置的目标亮度。
需要说明的是，一幅图像可以包括红绿蓝三个通道，上述第一亮度可以包括红绿蓝每个通道的第一通道亮度，反过来，通过一个像素位置的红绿蓝三个通道对应的第一通道亮度也可以合成为该像素位置的第一亮度。因此，可以首先计算得到每个像素位置的每个通道的目标单通道亮度，然后根据红绿蓝三个通道的目标单通道亮度合并计算得到该像素位置的目标亮度。
示例地，该待处理图像包括多个通道，上述第一亮度包括多个通道的第一通道亮度，上述目标反射亮度包括多个通道的目标通道反射亮度；可以针对该待处理图像的每个像素位置的每个通道，根据该第一通道亮度、该目标不透明度和该目标通道反射亮度，通过以下公式(1)计算得到该像素位置的该通道的目标单通道亮度：
XS
k＝(1-m)*XN
k+m*XD
k (1)；
其中，XS
k表示第k通道的目标单通道亮度，m表示该目标不透明度，XN
k表示该第k通道的第一通道亮度，XD
k表示该第k通道的目标通道反射亮度，k为正整数。
需要说明的是，在一种可选的实施方式中，上述XS
k、XN
k、XD
k和m的取值范围可以均为大于等于0且小于等于1的值。
然后可以将多个通道的目标单通道亮度合并得到该像素位置的目标亮度。具体的合并方式可以参考现有技术中将红绿蓝三个通道亮度合并的方式，本公开对此不再赘述。
通过上述方式，可以得到待处理图像的每个像素位置的目标亮度，从而完成对待处理图像的阴影处理，使得处理后的目标阴影图像更加逼真地反应阴影效果。
进一步地，上述目标不透明度可以为多个，上述预设阴影衰减参数也可以为多个，这样，根据多个目标不透明度和多个阴影衰减参数随机组合，可以得到多个目标阴影图 像，从而得到更加丰富的目标阴影图像，进一步提高阴影图像获取的效率。
在本公开的另一实施例中，上述透光信息可以包括待处理图像的每个像素位置的目标透明度。这样，可以针对待处理图像的每个像素位置的每个通道，根据上述第一通道亮度、目标透明度和目标通道反射亮度，通过以下公式(2)计算得到该像素位置的该通道的目标单通道亮度：
XS
k＝n*XN
k+(1-n)*XD
k (2)；
其中，XS
k表示第k通道的目标单通道亮度，n表示该目标透明度，XN
k表示该第k通道的第一通道亮度，XD
k表示该第k通道的目标通道反射亮度，k为正整数。
然后同样可以将多个通道的目标单通道亮度合并得到该像素位置的目标亮度。
在本公开的另一实施例中，该预设阴影衰减参数包括预设直接反射亮度和预设环境光衰减因子，该预设直接反射亮度用于表征该目标对象在该预设光照环境下对直接照明光源的反射光亮度，该预设直接反射亮度可以包括每个通道的预设直接反射亮度，该预设环境光衰减因子用于表征环境照明光源在该预设光照环境下的衰减因子。
需要说明的是，该预设光照环境可以包括预设光源和预设遮挡物，该预设光源可以包括直接照明光源和环境照明光源；根据上述目标对象的位置、材质和形状，可以确定该目标对象对直接照明光源的反射光亮度，可以将该反射光亮度作为上述预设直接反射亮度。根据预设遮挡物的位置、材质和形状属性，可以确定该预设遮挡物对环境照明光源的衰减因子，可以将该衰减因子作为该预设环境光衰减因子。
进一步地，根据不同的目标对象的位置、材质和形状，可以确定多个预设直接反射亮度。同样地，根据多个预设遮挡物的位置、材质和形状，可以得到多个不同的预设环境光衰减因子。
在上述S1022步骤中，可以根据该预设直接反射亮度、该预设环境光衰减因子和该第一亮度，获取每个像素位置的目标反射亮度。
示例地，该预设直接反射亮度可以包括每个通道的预设直接反射通道亮度；可以针对每个像素位置，根据该预设直接反射通道亮度、该预设环境光衰减因子和上述第一通道亮度，通过以下公式(3)计算得到该像素位置的每个通道的目标通道反射亮度：
其中，XD
k表示该第k通道的目标通道反射亮度，XN
k表示该第k通道的第一通道亮度，α
k表示该第k通道的预设直接反射通道亮度，γ表示该预设环境光衰减因子，k为正 整数。
然后，可以将多个通道的目标通道反射亮度作为该像素位置的目标反射亮度。
这样，可以通过预设直接反射亮度和预设环境光衰减因子，得到与目标对象更加接近的目标反射亮度，以便使得最终获取的目标阴影图像更加逼真。
图3是根据图1所示实施例示出的一种S101步骤的流程图，如图3所示，上述S101步骤可以包括以下步骤：
S1011、确定预设光照环境。
其中，该预设光照环境可以包括预设光源、预设遮挡物、预设相机和预设虚拟平面。
示例地，在本步骤中，可以通过Blender(三维图形图像软件)构建该预设光照环境，例如，在Blender中根据预设的形状、大小和相对位置信息，放置一个预设光源、一个或多个预设遮挡物、一个预设相机、以及一个虚拟平面，可以构造出该预设光照环境。例如，图4是根据一示例性实施例示出的一种预设光照环境的示意图，如图4所示，该预设光照环境可以包括预设光源401、预设遮挡物402、预设相机403和预设虚拟平面404。
S1012、在该预设光照环境中，通过预设相机捕获预设虚拟平面内每个像素位置的模型亮度。
S1013、根据该预设虚拟平面和该模型亮度，确定待处理图像在该预设光照环境下的透光信息。
示例地，可以将每个像素位置的模型亮度归一化为0到1之间的数值，将归一化后的数值作为该像素位置的透光信息。若该透光信息包括目标不透明度，则在上述归一化处理时，模型亮度越高，归一化后的数值越小；若该透光信息包括目标透明度，则在上述归一化处理时，模型亮度越小，归一化后的数值越小。
进一步地，可以通过对预设光照环境中的四个组件(预设光源、预设遮挡物、预设相机和预设虚拟平面)进行随机缩放、平移和旋转操作，从而得到不同的透光信息，以便根据不同的透光信息生成多个目标阴影图像。
需要说明的是，该透光信息可以以阴影蒙版的形式存储。例如，通过多个不同的阴影蒙版存储不同的透光信息，以便获取丰富多样的目标阴影图像。
综上所述，采用本公开上述实施例中的任一方法，获取待处理图像在预设光照环境下的透光信息；根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像；其中，该预设阴影衰减参数用于表征该待处理 图像中的目标对象在该预设光照环境下的反射系数。由于上述预设阴影衰减参数可以表征该待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
图5是根据一示例性实施例示出的一种图像处理装置500的框图，如图5所示，该装置500可以包括：
信息获取模块501，被配置为获取待处理图像在预设光照环境下的透光信息；
图像处理模块502，被配置为根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像；其中，该预设阴影衰减参数用于表征该待处理图像中的目标对象在该预设光照环境下的反射系数。
可选地，该透光信息包括该待处理图像的每个像素位置的目标不透明度；该图像处理模块502，被配置为根据预设阴影衰减参数确定每个该像素位置的目标反射亮度，该目标反射亮度用于表征该待处理图像中的目标对象在该预设光照环境下的反射光亮度；根据该目标不透明度和该目标反射亮度，对该待处理图像进行阴影处理，得到该目标阴影图像。
可选地，该图像处理模块502，被配置为根据该待处理图像的每个像素位置的第一亮度、该目标不透明度和该目标反射亮度，获取每个像素位置的目标亮度；根据多个像素位置的目标亮度，生成该目标阴影图像。
可选地，该待处理图像包括多个通道，该第一亮度包括多个通道的第一通道亮度，该目标反射亮度包括多个通道的目标通道反射亮度；该图像处理模块502，被配置为针对该待处理图像的每个像素位置的每个通道，根据该第一通道亮度、该目标不透明度和该目标通道反射亮度，通过以下公式计算得到该像素位置的该通道的目标单通道亮度：XS
k＝(1-m)*XN
k+m*XD
k；其中，XS
k表示第k通道的目标单通道亮度，m表示该目标不透明度，XN
k表示该第k通道的第一通道亮度，XD
k表示该第k通道的目标通道反射亮度，k为正整数；将多个通道的单通道亮度合并得到该像素位置的目标亮度。
可选地，该预设阴影衰减参数包括预设直接反射亮度和预设环境光衰减因子，该预设直接反射亮度用于表征该目标对象在该预设光照环境下对直接照明光源的反射光亮度，该预设环境光衰减因子用于表征环境照明光源在该预设光照环境下的衰减因子；该图像处理模块502，被配置为根据该预设直接反射亮度、该预设环境光衰减因子和该第一亮度， 获取每个像素位置的目标反射亮度。
可选地，该预设直接反射亮度包括每个通道的预设直接反射通道亮度；该图像处理模块502，被配置为针对每个像素位置，根据该预设直接反射通道亮度、该预设环境光衰减因子和该第一通道亮度，通过以下公式计算得到该像素位置的每个通道的目标通道反射亮度：
其中，XD
k表示该第k通道的目标通道反射亮度，XN
k表示该第k通道的第一通道亮度，α
k表示该第k通道的预设直接反射通道亮度，γ表示该预设环境光衰减因子，k为正整数；将多个通道的目标通道反射亮度作为该像素位置的目标反射亮度。
可选地，该信息获取模块501，被配置为确定预设光照环境，该预设光照环境包括预设光源、预设遮挡物、预设相机和预设虚拟平面；在该预设光照环境中，通过该预设相机捕获该预设虚拟平面内每个像素位置的模型亮度；根据该预设虚拟平面和该模型亮度，确定该待处理图像在该预设光照环境下的透光信息。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
综上所述，采用本公开上述实施例中的装置，获取待处理图像在预设光照环境下的透光信息；根据预设阴影衰减参数和该透光信息，对该待处理图像进行阴影处理，得到该待处理图像对应的目标阴影图像；其中，该预设阴影衰减参数用于表征该待处理图像中的目标对象在该预设光照环境下的反射系数。由于上述预设阴影衰减参数可以表征该待处理图像中的目标对象在预设光照环境下的反射系数，因此，可以得到与实际预设光照环境相匹配的目标阴影图像，并且由于无需人工拍摄，可以提高阴影图像获取的效率。
需要说明的是的，本公开中的终端可以是智能手机、平板电脑、智能手表、智能手环、PDA(Personal Digital Assistant，个人数字助理)、CPE(Customer Premise Equipment，客户终端设备)等电子设备，本公开对此不作限定。
本公开还提供一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现本公开提供的图像处理方法的步骤。
图6是根据一示例性实施例示出的电子设备600的框图。例如，电子设备600可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理、路由器等。
参照图6，电子设备600可以包括以下一个或多个组件：处理组件602，存储器604，电力组件606，多媒体组件608，音频组件610，输入/输出(I/O)接口612，传感器组件 614，以及通信组件616。
处理组件602通常控制电子设备600的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件602可以包括一个或多个处理器620来执行指令，以完成上述图像处理方法的全部或部分步骤。此外，处理组件602可以包括一个或多个模块，便于处理组件602和其他组件之间的交互。例如，处理组件602可以包括多媒体模块，以方便多媒体组件608和处理组件602之间的交互。
存储器604被配置为存储各种类型的数据以支持在电子设备600的操作。这些数据的示例包括用于在电子设备600上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器604可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电力组件606为电子设备600的各种组件提供电力。电力组件606可以包括电源管理系统，一个或多个电源，及其他与为电子设备600生成、管理和分配电力相关联的组件。
多媒体组件608包括在所述电子设备600和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件608包括一个前置摄像头和/或后置摄像头。当电子设备600处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件610被配置为输出和/或输入音频信号。例如，音频组件610包括一个麦克风(MIC)，当电子设备600处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器604或经由通信组件616发送。在一些实施例中，音频组件610还包括一个扬声器，用于输出音频信号。
I/O接口612为处理组件602和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件614包括一个或多个传感器，用于为电子设备600提供各个方面的状态评估。例如，传感器组件614可以检测到电子设备600的打开/关闭状态，组件的相对定位，例如所述组件为电子设备600的显示器和小键盘，传感器组件614还可以检测电子设备600或电子设备600一个组件的位置改变，用户与电子设备600接触的存在或不存在，电子设备600方位或加速/减速和电子设备600的温度变化。传感器组件614可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件614还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件614还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件616被配置为便于电子设备600和其他设备之间有线或无线方式的通信。电子设备600可以接入基于通信标准的无线网络，例如Wi-Fi，2G、3G、4G、5G、NB-IOT、eMTC、或其他6G等，或它们的组合。在一个示例性实施例中，通信组件616经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件616还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备600可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述图像处理方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器604，上述指令可由电子设备600的处理器620执行以完成上述图像处理方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在另一示例性实施例中，还提供一种计算机程序产品，该计算机程序产品包含能够由可编程的装置执行的计算机程序，该计算机程序具有当由该可编程的装置执行时用于 执行上述图像处理方法的步骤的代码部分。
本领域技术人员在考虑说明书及实践本公开后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。
Claims (11)
- 一种图像处理方法，所述方法包括：获取待处理图像在预设光照环境下的透光信息；根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像；其中，所述预设阴影衰减参数用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射系数。
- 根据权利要求1所述的方法，其中，所述透光信息包括所述待处理图像的每个像素位置的目标不透明度；所述根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像包括：根据预设阴影衰减参数确定每个所述像素位置的目标反射亮度，所述目标反射亮度用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射光亮度；根据所述目标不透明度和所述目标反射亮度，对所述待处理图像进行阴影处理，得到所述目标阴影图像。
- 根据权利要求2所述的方法，其中，所述根据所述目标不透明度和所述目标反射亮度，对所述待处理图像进行阴影处理，得到所述目标阴影图像包括：根据所述待处理图像的每个像素位置的第一亮度、所述目标不透明度和所述目标反射亮度，获取每个像素位置的目标亮度；根据多个像素位置的目标亮度，生成所述目标阴影图像。
- 根据权利要求3所述的方法，其中，所述待处理图像包括多个通道，所述第一亮度包括多个通道的第一通道亮度，所述目标反射亮度包括多个通道的目标通道反射亮度；所述根据所述待处理图像的每个像素位置的第一亮度、所述目标不透明度和所述目标反射亮度，获取每个像素位置的目标亮度包括：针对所述待处理图像的每个像素位置的每个通道，根据所述第一通道亮度、所述目标不透明度和所述目标通道反射亮度，通过以下公式计算得到该像素位置的该通道的目标单通道亮度：XS k＝(1-m)*XN k+m*XD k；其中，XS k表示第k通道的目标单通道亮度，m表示所述目标不透明度，XN k表示所 述第k通道的第一通道亮度，XD k表示所述第k通道的目标通道反射亮度，k为正整数；将多个通道的目标单通道亮度合并得到该像素位置的目标亮度。
- 根据权利要求4所述的方法，其中，所述预设阴影衰减参数包括预设直接反射亮度和预设环境光衰减因子，所述预设直接反射亮度用于表征所述目标对象在所述预设光照环境下对直接照明光源的反射光亮度，所述预设环境光衰减因子用于表征环境照明光源在所述预设光照环境下的衰减因子；所述根据预设阴影衰减参数确定每个像素位置的目标反射亮度包括：根据所述预设直接反射亮度、所述预设环境光衰减因子和所述第一亮度，获取每个像素位置的目标反射亮度。
- 根据权利要求5所述的方法，其中，所述预设直接反射亮度包括每个通道的预设直接反射通道亮度；所述根据所述预设直接反射亮度、所述预设环境光衰减因子和所述第一亮度，获取每个像素位置的目标反射亮度包括：针对每个像素位置，根据所述预设直接反射通道亮度、所述预设环境光衰减因子和所述第一通道亮度，通过以下公式计算得到该像素位置的每个通道的所述目标通道反射亮度：
其中，XD k表示所述第k通道的目标通道反射亮度，XN k表示所述第k通道的第一通道亮度，α k表示所述第k通道的预设直接反射通道亮度，γ表示所述预设环境光衰减因子；将多个通道的目标通道反射亮度作为该像素位置的目标反射亮度。 - 根据权利要求1至6中任一项所述的方法，其中，所述获取待处理图像在预设光照环境下的透光信息包括：确定预设光照环境，所述预设光照环境包括预设光源、预设遮挡物、预设相机和预设虚拟平面；在所述预设光照环境中，通过所述预设相机捕获所述预设虚拟平面内每个像素位置的模型亮度；根据所述预设虚拟平面和所述模型亮度，确定所述待处理图像在所述预设光照环境 下的透光信息。
- 一种图像处理装置，所述装置包括：信息获取模块，被配置为获取待处理图像在预设光照环境下的透光信息；图像处理模块，被配置为根据预设阴影衰减参数和所述透光信息，对所述待处理图像进行阴影处理，得到所述待处理图像对应的目标阴影图像；其中，所述预设阴影衰减参数用于表征所述待处理图像中的目标对象在所述预设光照环境下的反射系数。
- 一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为执行权利要求1至7中任一项所述方法的步骤。
- 一种计算机可读存储介质，其上存储有计算机程序指令，该程序指令被处理器执行时实现权利要求1至7中任一项所述方法的步骤。
- 一种计算机程序产品，该计算机程序产品包含能够由可编程的装置执行的计算机程序，该计算机程序具有当由该可编程的装置执行时用于执行权利要求1至7中任一项所述方法的步骤的代码部分。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111521335.4A CN116263941A (zh) | 2021-12-13 | 2021-12-13 | 图像处理方法、装置、存储介质及电子设备 |
| CN202111521335.4 | 2021-12-13 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023108992A1 true WO2023108992A1 (zh) | 2023-06-22 |
Family
ID=86723216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/090722 WO2023108992A1 (zh) | 2021-12-13 | 2022-04-29 | 图像处理方法、装置、存储介质、电子设备和程序产品 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116263941A (zh) |
| WO (1) | WO2023108992A1 (zh) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004070670A (ja) * | 2002-08-06 | 2004-03-04 | Namco Ltd | 画像生成システム、プログラム及び情報記憶媒体 |
| US20110164811A1 (en) * | 2008-09-03 | 2011-07-07 | Nec Corporation | Image processing device, image processing method and image processing program |
| US20160350962A1 (en) * | 2015-05-29 | 2016-12-01 | General Electric Company | Method and systems for shading and shadowing volume-rendered images based on a viewing direction |
| CN108573480A (zh) * | 2018-04-20 | 2018-09-25 | 太平洋未来科技（深圳）有限公司 | 基于图像处理的环境光补偿方法、装置及电子设备 |
| CN110009723A (zh) * | 2019-03-25 | 2019-07-12 | 阿里巴巴集团控股有限公司 | 环境光源的重建方法及装置 |
| CN111105365A (zh) * | 2019-12-05 | 2020-05-05 | 深圳积木易搭科技技术有限公司 | 一种纹理影像的色彩校正方法、介质、终端和装置 |
| CN113674718A (zh) * | 2021-08-10 | 2021-11-19 | 北京小米移动软件有限公司 | 显示亮度调整方法、装置及存储介质 |
-
2021
- 2021-12-13 CN CN202111521335.4A patent/CN116263941A/zh active Pending
-
2022
- 2022-04-29 WO PCT/CN2022/090722 patent/WO2023108992A1/zh unknown
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004070670A (ja) * | 2002-08-06 | 2004-03-04 | Namco Ltd | 画像生成システム、プログラム及び情報記憶媒体 |
| US20110164811A1 (en) * | 2008-09-03 | 2011-07-07 | Nec Corporation | Image processing device, image processing method and image processing program |
| US20160350962A1 (en) * | 2015-05-29 | 2016-12-01 | General Electric Company | Method and systems for shading and shadowing volume-rendered images based on a viewing direction |
| CN108573480A (zh) * | 2018-04-20 | 2018-09-25 | 太平洋未来科技（深圳）有限公司 | 基于图像处理的环境光补偿方法、装置及电子设备 |
| CN110009723A (zh) * | 2019-03-25 | 2019-07-12 | 阿里巴巴集团控股有限公司 | 环境光源的重建方法及装置 |
| CN111105365A (zh) * | 2019-12-05 | 2020-05-05 | 深圳积木易搭科技技术有限公司 | 一种纹理影像的色彩校正方法、介质、终端和装置 |
| CN113674718A (zh) * | 2021-08-10 | 2021-11-19 | 北京小米移动软件有限公司 | 显示亮度调整方法、装置及存储介质 |
Non-Patent Citations (2)
| Title |
|---|
| LI, WENBIN ET AL.: "Shadow Elimination by Chrominance Distortion and Local Kullback-Leibler Divergence", JOURNAL OF COMPUTER APPLICATIONS, no. 5, 31 May 2007 (2007-05-31), XP009547147 * |
| WANG HAIBIN; LENG BIN; HU YOUPAN; HE QING; WU WENKAI; GUAN GUAN; ZOU HEHUI: "Shadow removal based on the luminance, texture and color-ratio of the pix", 2013 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA), IEEE, 26 August 2013 (2013-08-26), pages 762 - 766, XP032558920, DOI: 10.1109/ICInfA.2013.6720396 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116263941A (zh) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11114130B2 (en) | Method and device for processing video | |
| WO2022179026A1 (zh) | 图像处理方法及装置、电子设备和存储介质 | |
| CN109345485B (zh) | 一种图像增强方法、装置、电子设备及存储介质 | |
| CN104639843B (zh) | 图像处理方法及装置 | |
| JP7166171B2 (ja) | インタフェース画像の表示方法、装置及びプログラム | |
| WO2018120238A1 (zh) | 用于处理文档的设备、方法和图形用户界面 | |
| CN113160094A (zh) | 图像处理方法及装置、电子设备和存储介质 | |
| US11308692B2 (en) | Method and device for processing image, and storage medium | |
| KR20140088768A (ko) | 카메라를 실행하기 위한 방법 및 그 전자 장치 | |
| WO2022077970A1 (zh) | 特效添加方法及装置 | |
| CN107967459B (zh) | 卷积处理方法、装置及存储介质 | |
| CN109472738B (zh) | 图像光照校正方法及装置、电子设备和存储介质 | |
| CN113965694B (zh) | 录像方法、电子设备及计算机可读存储介质 | |
| CN108734754A (zh) | 图像处理方法及装置 | |
| CN105957037B (zh) | 图像增强方法及装置 | |
| CN110609649B (zh) | 界面显示方法、装置及存储介质 | |
| WO2022156150A1 (zh) | 图像处理方法及装置、电子设备、存储介质及计算机程序 | |
| CN107341777A (zh) | 图片处理方法及装置 | |
| WO2021189995A1 (zh) | 视频渲染方法、装置、电子设备及存储介质 | |
| CN113132704A (zh) | 一种图像处理的方法、装置、终端以及存储介质 | |
| CN111338743B (zh) | 一种界面处理方法、装置及存储介质 | |
| WO2023005850A1 (zh) | 图像处理方法及装置、电子设备、存储介质及计算机程序产品 | |
| US10204403B2 (en) | Method, device and medium for enhancing saturation | |
| CN107219989B (zh) | 图标处理方法、装置及终端 | |
| CN106982327A (zh) | 图像处理方法和装置 |
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: 22905760 Country of ref document: EP Kind code of ref document: A1 |