Image Processing Method, Apparatus, Electronic Device, and Storage Medium

Abstract

The present invention provides an image processing method, apparatus, electronic device and storage medium. The method includes: obtaining a reference surface model of a first bone pose of an animated character; obtaining a second bone pose of the animated character; generating an exemplary surface model of the second bone pose based on the reference surface model and the second bone pose; obtaining a pose transformation matrix between the first bone pose and the second bone pose; and based on the pose transformation matrix, converting the exemplary surface model and the reference surface model to the same coordinate space to call the reference surface model and the exemplary surface model in the coordinate space for generating the animated character. The embodiments of the present invention improve the compatibility of bone animation with surface deformation.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an image processing method, apparatus, electronic device and storage medium. Background Art

[0002] With the rapid development of information technology, the general audience has higher and higher requirements for animated characters - they should be more and more realistic, more and more vivid, and more and more artistically expressive. For animated characters that mainly rely on visual output information, to meet the above requirements of the audience, the most direct way is to improve the artistic expressiveness of animated characters from the visual level. In this process, to meet specific artistic needs, various complex non-linear surface deformations are often applied to animated characters during the generation stage. In the prior art, especially in the field of skeletal animation, the compatibility of non-linear surface deformations during the generation stage of animated characters is low, and the needs of animated character generation cannot be effectively met. Summary of the Invention

[0003] An object of the present invention is to provide an image processing method, apparatus, electronic device and storage medium, which can improve the compatibility of skeletal animation with surface deformation.

[0004] According to an aspect of an embodiment of the present invention, an image processing method is disclosed, including:

[0005] Obtaining a reference surface model of a first bone pose of an animated character;

[0006] Obtaining a second bone pose of the animated character;

[0007] Generating an example surface model of the second bone pose based on the reference surface model and the second bone pose;

[0008] Obtaining a pose transformation matrix between the first bone pose and the second bone pose;

[0009] Based on the pose transformation matrix, converting the example surface model and the reference surface model to the same coordinate space, so as to call the reference surface model and the example surface model in the coordinate space for the generation of the animated character.

[0010] According to an aspect of an embodiment of the present invention, an image processing apparatus is disclosed, including:

[0011] A first obtaining module configured to obtain a reference surface model of a first bone pose of an animated character;

[0012] A second obtaining module configured to obtain a second bone pose of the animated character;

[0013] A generation module, configured to generate an exemplary surface model of the second bone pose based on the reference surface model and the second bone pose;

[0014] A third acquisition module, configured to acquire a pose transformation matrix between the first bone pose and the second bone pose;

[0015] A storage module, configured to convert the exemplary surface model and the reference surface model to the same coordinate space based on the pose transformation matrix, so as to call the reference surface model and the exemplary surface model in the coordinate space to generate the animated character.

[0016] According to an aspect of an embodiment of the present invention, an image processing electronic device is disclosed, including: a memory storing computer-readable instructions; a processor reading the computer-readable instructions stored in the memory to execute the method described in the above embodiments.

[0017] According to an aspect of an embodiment of the present invention, a computer-readable storage medium is disclosed, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor of a computer, the computer is made to execute the method described in the above embodiments.

[0018] In an embodiment of the present invention, in the production stage of material resources for generating an animated character, after an image processing terminal generates an exemplary surface model according to a reference surface model, the exemplary surface model and the reference surface model are converted to the same coordinate space based on a pose transformation matrix between a first bone pose (the bone pose of the reference surface model) and a second bone pose (the bone pose of the exemplary surface model). This enables the produced material resources to skip the influence of additional surface deformation, so that in the animated character generation stage, complex non-linear additional surface deformation can be compatible, improving the compatibility of bone animation with surface deformation.

[0019] Other features and advantages of the present invention will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0020] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other objects, features and advantages of the present invention will become more apparent.

[0022] Figure 1 Shows the composition of the basic architecture according to an embodiment of the present invention.

[0023] Figure 2Shows the architecture composition in a game scenario according to an embodiment of the present invention.

[0024] Figure 3 Shows a flowchart of an image processing method according to an embodiment of the present invention.

[0025] Figure 4 Shows a flowchart of the material resource production stage according to an embodiment of the present invention.

[0026] Figure 5 Shows a flowchart of the animation character generation stage according to an embodiment of the present invention.

[0027] Figure 6 Shows a terminal interface diagram of applying the image processing method to Maya software for animation generation according to an embodiment of the present invention.

[0028] Figure 7 Shows a block diagram of an image processing apparatus according to an embodiment of the present invention.

[0029] Figure 8 Shows a hardware diagram of an image processing electronic device according to an embodiment of the present invention. Detailed implementation manners

[0030] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present invention will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted.

[0031] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more example embodiments. In the following description, many specific details are provided to give a thorough understanding of the example embodiments of the present invention. However, those skilled in the art will realize that the technical solutions of the present invention can be practiced without one or more of the specific details, or other methods, components, steps, etc. can be adopted. In other cases, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring the various aspects of the present invention.

[0032] Some of the block diagrams shown in the drawings are functional entities and do not necessarily have to correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0033] First, some concepts related to the embodiments of the present invention are briefly described.

[0034] Animated character: A virtual character mainly generated based on three-dimensional image technology through a game engine, drawing software, or other image processing tools. The image processing method proposed in the embodiments of the present invention mainly targets the image processing process of animated characters in skeletal animation.

[0035] Skeletal animation: Skeletal animation is a type of model animation. In skeletal animation, an animated character includes at least two types of data: bone pose and surface model. Among them, the bone pose describes the orientation and position of the "bones" of the animated character; the surface model describes the vertices on the surface of the animated character. The change in the bone pose can correspondingly drive the change in the surface model, so that by driving the bone pose, the corresponding animation can be generated.

[0036] Skinning process: From the brief description of skeletal animation, it can be known that the change in the bone pose can correspondingly drive the change in the surface model. To achieve this, it is necessary to define which vertices on the surface can be driven by specific bones, and the process of defining which vertices on the surface can be driven by specific bones is the skinning process.

[0037] Extra surface deformation: When generating an animated character, it may be necessary to add extra surface deformation to the animated character to meet specific business requirements. For example, after the skinning process and other necessary processing processes, an animated character with a plump figure can already be generated. However, according to the business requirements - when the animated character moves, the fat on its waist can shake like in real life. Even further, shake more exaggeratedly than in real life to meet artistic requirements. In this case, it is necessary to add extra surface deformation on the animated character that can simulate the shaking of the fat. It can be understood that in practical applications, a considerable part of the extra surface deformations are non-linear surface deformations, and even complex non-linear surface deformations that are difficult to capture the deformation rules.

[0038] It should be noted that before actually generating an animated character, relevant material resources will be pre-produced, and the animated character will be generated based on the pre-produced material resources. In the embodiments of the present invention, the material resources are the reference surface model and the example surface model. Among them, the reference surface model is the most basic pre-set material resource, usually there is only one; the example surface model is the material resource further obtained based on the reference surface model, there is at least one, and usually there are two or more.

[0039] Figure 1 The basic system architecture composition of an embodiment of the present invention is shown: the first user terminal 10, the cloud server 20, and the second user terminal 20.

[0040] Material resource production stage: mainly involves the first user terminal 10 and the cloud server 20. Among them, the first user terminal 10 mainly serves as the front end to produce material resources; the cloud server 20 mainly serves as the back end, provides corresponding functional support for the first user terminal 10 during the production of material resources, and stores the material resources produced by the first user terminal 10.

[0041] Animated character generation stage: mainly involves the second user terminal 30 and the cloud server 20. Among them, the cloud server 20 mainly serves as the back end, generates an animated character according to the stored material resources, and sends the rendering data of the animated character to the second user terminal 30 for the second user terminal 30 to render and display the animated character; the second user terminal 30 mainly serves as the front end, renders according to the rendering data received from the cloud server 20, and displays the animated character.

[0042] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0043] Figure 2 The system architecture composition of an embodiment of the present invention in a game scenario is shown: the modeler terminal 10, the game server 20, and the game terminal 30.

[0044] Material resource production stage: mainly involves the modeler terminal 10 and the cloud server 20. Among them, the modeler terminal 10 mainly serves as the front end for the modeler to produce game material resources (for example: the surface model of a game character in a natural standing pose, the surface model of a game character with outstretched arms); the cloud server 20 mainly serves as the back end, provides corresponding functional support for the modeler terminal 10 during the production of game material resources, and stores the game material resources produced by the modeler terminal 10.

[0045] Among them, the modeler can perform corresponding art work on the modeler terminal 10 (for example: modifying the surface model of the game character through a digital painting board, modifying the surface model of the game character through mouse instructions and keyboard instructions), and with the support of the cloud server 20, produce corresponding game material resources.

[0046] Animation character generation stage: mainly involves the game terminal 30 and the cloud server 20. Among them, the cloud server 20 mainly serves as the backend, generates game characters according to the stored game material resources, and sends the rendering data of the game characters to the game terminal 30 for the game terminal 30 to render and display the game characters; the game terminal 30 mainly serves as the front end, renders according to the rendering data received from the cloud server 20, and displays the game characters.

[0047] Among them, players can perform game operations on the game terminal 30 (for example: controlling the movement of the game character through the mouse, releasing the skills of the game character through the keyboard, controlling the movement and skill release of the game character through screen touch), to control the actions of the game characters in the game terminal 30. The game terminal 30 responds to the player's game operations, generates corresponding instructions, and uploads the instructions to the cloud server 20. The cloud server 20 then generates game characters based on the instructions and the game material resources.

[0048] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0049] The execution subject of the embodiment of the present invention is an image processing terminal. Through the above description of the system architecture of the embodiment of the present invention, it can be seen that the image processing terminal can be a combination of multiple terminals. For example: in the material resource production stage, the image processing terminal can be a combination of the first user terminal and the cloud server; in the animation character generation stage, the image processing terminal can be a combination of the second user terminal and the cloud server.

[0050] It should be noted that according to different specific application scenarios, the image processing terminal in the material resource production stage is not necessarily a combination of the first user terminal and the cloud server; the image processing terminal in the animation character generation stage is not necessarily a combination of the second user terminal and the cloud server.

[0051] As Figure 3 shown, an image processing method includes:

[0052] Step 410, obtain the reference surface model of the first bone pose of the animation character;

[0053] Step 420, obtain the second bone pose of the animation character;

[0054] Step 430: Generate an example surface model of the second bone pose based on the reference surface model and the second bone pose;

[0055] Step 440: Obtain the pose transformation matrix between the first bone pose and the second bone pose;

[0056] Step 450: Based on the pose transformation matrix, transform the example surface model and the reference surface model to the same coordinate space, so as to call the reference surface model and the example surface model in the coordinate space to generate the animated character.

[0057] In the embodiment of the present invention, in the material resource production stage for generating an animated character, after the image processing terminal generates an example surface model according to the reference surface model, the example surface model and the reference surface model are transformed to the same coordinate space based on the pose transformation matrix between the first bone pose (the bone pose of the reference surface model) and the second bone pose (the bone pose of the example surface model). This enables the produced material resources to skip the influence of additional surface deformation, so that in the animated character generation stage, complex non-linear additional surface deformation can be compatible, improving the compatibility of bone animation with surface deformation.

[0058] The following describes the specific implementation process of the material resource production stage.

[0059] In step 410, obtain the reference surface model of the first bone pose of the animated character.

[0060] The reference surface model refers to the surface model used as the reference for material resource production; the first bone pose refers to the bone pose of the reference surface model. For example: the reference surface model is the surface model of the animated character in the natural standing pose, and the first bone pose is the bone pose of the animated character in the natural standing pose.

[0061] In the embodiment of the present invention, the reference surface model can be pre-generated and stored in the image processing terminal. When performing material resource production, the image processing terminal can retrieve this reference surface model; it can also be made in real time by the user (for example, a modeler engaged in art work) on the image processing terminal.

[0062] In step 420, obtain the second bone pose of the animated character.

[0063] The second bone pose refers to the bone pose of the example surface model to be generated; the example surface model refers to a surface model generated with reference to the reference surface model and having a bone pose other than the first bone pose. For example: the reference surface model is the surface model of an animated character in a natural standing pose. With reference to the surface model of the animated character in a natural standing pose, the surface model of the animated character in a horizontal arm pose is an example surface model. Correspondingly, the bone pose of the animated character in a horizontal arm pose is the second bone pose.

[0064] In an embodiment of the present invention, the second bone pose can be pre-generated and stored in the image processing terminal; or it can be made in real time by a user (such as a modeler engaged in art work) on the image processing terminal.

[0065] In step 430, based on the reference surface model and the second bone pose, an example surface model of the second bone pose is generated.

[0066] In one embodiment, generating an example surface model of the second bone pose based on the reference surface model and the second bone pose includes:

[0067] Performing skinning processing on the reference surface model based on the second bone pose to obtain an example bone skinning model of the second bone pose;

[0068] Extracting the surface data of the example bone skinning model and generating an example surface model of the second bone pose according to the surface data.

[0069] The bone skinning model refers to a model with bone skinning information after skinning processing. The bone skinning model mainly includes two parts of information: surface information and bone skinning information.

[0070] In this embodiment, based on the obtained second bone pose, skinning processing is performed on the obtained reference surface model to obtain an example bone skinning model of the second bone pose with bone skinning information. For example: the reference surface model is a horizontal arm model in a horizontal pose, and the second bone pose is the bone pose of an upward arm in an upward pose. Skinning processing is performed on the horizontal arm model based on the bone pose of the upward arm to obtain an upward arm model in an upward pose with bone skinning information.

[0071] After obtaining the example bone skinning model of the second bone pose, extracting its surface data, an example surface model of the second bone pose can be generated according to the surface data.

[0072] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and usage scope of the present invention.

[0073] In one embodiment, before extracting the surface data of the exemplary skeletal skinning model, the following steps are further included:

[0074] Obtain a modification request from the requester for the exemplary skeletal skinning model;

[0075] If the verification of the modification request passes, open the modification permission of the exemplary skeletal skinning model to the requester, so that the requester can modify the exemplary skeletal skinning model.

[0076] Extract the surface data of the exemplary skeletal skinning model to obtain the exemplary surface model of the second bone pose, including: extracting the surface data of the modified exemplary skeletal skinning model.

[0077] In this embodiment, after performing skinning processing on the reference surface model to obtain the exemplary skeletal skinning model and before extracting the surface data to obtain the exemplary surface model, the requester (for example, the modeler terminal at the front end) can be allowed to modify the exemplary skeletal skinning model.

[0078] Specifically, the skinning process itself is a linear mathematical process. Therefore, the exemplary skeletal skinning model obtained through skinning only makes simple changes in bone pose, and its surface may not meet specific artistic requirements. For example: performing skinning processing on a horizontal arm model based on the bone pose of an elbow bend can obtain a bent arm model with bone skinning information and an elbow bend pose. The biceps brachii of the horizontal arm model is relatively flat, and the biceps brachii of the bent arm model obtained only after skinning hardly changes significantly and remains relatively flat. It can be understood that when the elbow bends, it will compress the muscles. Compared with the horizontal arm model, the biceps brachii of the bent arm model should bulge significantly. If there are specific artistic requirements, the degree of bulge of the biceps brachii of the bent arm model is also required to be more obvious.

[0079] Therefore, after skinning processing, the image processing terminal allows the requester to modify the exemplary skinned bone model to meet the corresponding artistic requirements. Specifically, the user requests to modify the exemplary skeletal skinning model through the requester. After the verification passes, the corresponding modification permission is opened to the requester, so that the user can modify the exemplary skeletal skinning model through the requester (for example, the modeler modifies the exemplary skeletal skinning model after skinning processing according to artistic needs through the modeler terminal at the front end). During the process of the user modifying the exemplary skeletal skinning model through the requester, the surface of the exemplary skeletal skinning model can be modified; or the second bone pose of the exemplary skeletal skinning model can be modified.

[0080] After the modification is completed, the image processing terminal then extracts the surface data of the modified exemplary skeletal skinning model to obtain the exemplary surface model of the modified second bone pose.

[0081] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and application scope of the present invention.

[0082] In step 440, an attitude transformation matrix between the first bone attitude and the second bone attitude is obtained.

[0083] The attitude transformation matrix refers to a mathematical matrix that describes the mutual transformation relationship between the first bone attitude and the second bone attitude. Through the attitude transformation matrix, the first bone attitude can be transformed into the second bone attitude, and the second bone attitude can also be transformed into the first bone attitude.

[0084] In the embodiment of the present invention, both the first bone attitude and the second bone attitude exist in the form of specific data in the image processing terminal. For example: the three-dimensional spatial coordinates of the bone vertices can be stored in the image processing terminal. By adjusting the three-dimensional spatial coordinates of the bone vertices, the corresponding bone attitude can be obtained, that is, the bone attitude can be stored and processed in the form of three-dimensional spatial coordinate data. Therefore, the first bone attitude can be represented as a mathematical matrix A, the second bone attitude can be represented as a mathematical matrix B, and according to A*C = B, the matrix C - the attitude transformation matrix is calculated.

[0085] In step 450, based on the attitude transformation matrix, the example surface model and the reference surface model are converted to the same coordinate space, so as to call the reference surface model and the example surface model from the coordinate space to generate the animated character.

[0086] In the embodiment of the present invention, in bone animation, it is necessary to convert the produced material resources to the same coordinate space for generating animated characters. That is, in the material resource production stage, the example surface model and the reference surface model need to be converted to the same coordinate space. Specifically, the example surface model can be stored in the reference coordinate space where the reference surface model is located.

[0087] In one embodiment, converting the example surface model and the reference surface model to the same coordinate space based on the attitude transformation matrix includes: using the attitude transformation matrix to perform coordinate transformation processing on the example surface model, and storing the example surface model in the reference coordinate space where the reference surface model is located.

[0088] In this embodiment, since the attitude transformation matrix describes the transformation relationship between the first bone attitude and the second bone attitude, the coordinate transformation processing can be performed on the example surface model through the attitude transformation matrix, and the coordinate space where the example surface model is located is converted to the coordinate space where the reference surface model is located, so as to store the example surface model in the coordinate space where the reference surface model is located.

[0089] Next, refer toFigure 4 Describe the process of the material resource production stage in an embodiment of the present invention.

[0090] As Figure 4 shown: The reference surface model M0 is located in the reference coordinate space. The data initially obtained by the image processing terminal includes - the reference surface model M0, the first bone pose P0 corresponding to the reference surface model M0, and the example surface model M i corresponding second bone pose P i .

[0091] According to the first bone pose P0 and the second bone pose P i , calculate the pose transformation matrix between the two, so as to perform coordinate space transformation in the subsequent process through this pose transformation matrix.

[0092] According to the second bone pose P i , perform skinning calculation on the reference surface model M0 to obtain an example bone skinning model; furthermore, the modeler can modify the example bone skinning model according to artistic needs to obtain a new example bone skinning model that meets the requirements. Apply the pose transformation matrix to transform the new example bone skinning model into the reference coordinate space, so as to obtain the example surface model M i in the reference coordinate space.

[0093] In this embodiment, the image processing terminal stores both the reference surface model M0 and the example surface model M i in the reference coordinate space through the pose transformation matrix, so that in the subsequent animation character generation process, a series of processes performed on the reference surface model M0 and the example surface model M i are all carried out in this reference coordinate space, thereby skipping the influence of surface deformation, so that the generated material resources - the reference surface model M0 and the example surface model M i can be compatible with any non-linear additional surface deformation.

[0094] It should be noted that this embodiment is only an exemplary description and should not limit the functions and application scope of the present invention.

[0095] Next, describe the specific implementation process of using the material resources in the animation character generation stage after the material resource production stage.

[0096] In an embodiment, calling the reference surface model and the example surface model from this coordinate space for the generation of this animation character includes:

[0097] Obtain the target bone pose of the animation character;

[0098] Skin the reference surface model based on the target bone pose to obtain a target bone skin model of the target bone pose;

[0099] Obtain the reference surface model and the example surface model in the coordinate space;

[0100] Based on the reference surface model and the example surface model, obtain a corrected surface model of the target bone pose;

[0101] Generate the animated character based on the target bone skin model and the corrected surface model.

[0102] The target bone pose refers to the bone pose after the generation of the animated character. For example: if the target bone pose is the bone pose in the standing posture with hands on the hips, then the bone pose of the generated animated character is the bone pose in the standing posture with hands on the hips. Correspondingly, the target bone skin model refers to the animated character model of the target bone pose with bone skin information.

[0103] The corrected surface model refers to a surface model that can make a certain degree of correction to the surface of the target bone skin model to meet the artistic requirements of the example surface model to a certain extent. The bone pose of the corrected surface model is basically the same as that of the target bone skin model, which is also the target bone pose. In one embodiment, the surface model of the artistic style of the target bone pose generated using pre-generated material resources of a specific artistic style is the corrected surface model in this embodiment.

[0104] In the embodiment of the present invention, in the stage of generating an animated character: the image processing terminal obtains the target bone pose of the animated character; skins the reference surface model to obtain a target bone skin model of the target bone pose; generates a corrected surface model based on the reference surface model and the example surface model (i.e., pre-generated material resources of a specific artistic style) in the same coordinate space; and then generates an animated character based on the target bone skin model and the corrected surface model.

[0105] Among them, since the reference surface model and the example surface model are located in the same independent coordinate space constructed by the pose transformation matrix, the processing of the reference surface model and the example surface model is carried out within this coordinate space and is not affected by surface deformation, so that the animated character based on this can be compatible with any non-linear surface deformation.

[0106] In one embodiment, obtaining the target bone pose of the animated character includes:

[0107] Obtain the control data input based on the input device;

[0108] Based on the control data, obtain the target bone pose of the animated character.

[0109] In this embodiment, the target bone pose is derived from the manipulation data input by the input device. Specifically, it is derived from the manipulation data of the input device of the second user terminal in the image processing terminal. The manipulation data includes: keyboard data, mouse data, and screen touch data.

[0110] For example: The player performs a screen touch operation on the mobile terminal (i.e., the second user terminal) to instruct the animated character in the mobile terminal game to make corresponding actions in a specific pose. The screen touch data triggered by the screen touch operation is uploaded to the cloud server, and the cloud server determines the specific pose indicated by the player, that is, the target bone pose of the animated character, based on the obtained screen touch data.

[0111] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and usage scope of the present invention.

[0112] In one embodiment, obtaining the target bone pose of the animated character includes:

[0113] Obtaining sensor data input by the sensor device;

[0114] Based on the sensor data, capturing the user's action;

[0115] Based on the user's action, obtaining the target bone pose of the animated character.

[0116] In this embodiment, the target bone pose is derived from the sensor data input by the sensor device. Specifically, it is derived from the sensor data input by the sensor device of the second user terminal in the image processing terminal. The sensor data may include: positioning sensor data related to positioning information, and motion sensor data related to local limb movements.

[0117] For example: The player wears a VR (Virtual Reality) device (such as: VR glasses, VR handle) that communicates with the computer terminal, and makes specific actions to instruct the corresponding game character in the VR game system running on the computer terminal to make corresponding actions. The corresponding VR sensor system (such as: a sensor system composed of at least two base stations) can generate corresponding sensor data by monitoring the sensors in the VR device (such as: the sensors in the VR handle). After the sensor data is uploaded to the cloud server through the computer terminal, the cloud server can capture the user's action and determine the bone pose corresponding to the captured user's action as the target bone pose of the game character.

[0118] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and usage scope of the present invention.

[0119] In one embodiment, based on the reference surface model and the exemplar surface model, obtaining a corrected surface model of the target bone pose includes:

[0120] Obtaining a first bone pose corresponding to the reference surface model and a second bone pose corresponding to the exemplar surface model;

[0121] Determining weights assigned to the first bone pose and the second bone pose respectively when fusing the first bone pose and the second bone pose into the target bone pose;

[0122] Based on the weights, fusing the reference surface model and the exemplar surface model to obtain the corrected surface model.

[0123] In this embodiment, the image processing terminal obtains the target bone pose P, the first bone pose P0 of the reference surface model M0, and the second bone pose P1 of the exemplar surface model M1; determines the weight W0 assigned to P0 and the weight W1 assigned to the pose P1 when fusing the first bone pose P0 and the second bone pose P1 into the target bone pose P; and then fuses M0 and M1 according to W0 and W1 to obtain the corrected surface model M. Among them, fusing M0 and M1 according to W0 and W1 to obtain the corrected surface model M can be performed in the manner of W0 * M0 + W1 * M1 = M.

[0124] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and application scope of the present invention.

[0125] In one embodiment, based on the target bone skinning model and the corrected surface model, generating the animated character includes:

[0126] Obtaining a pose transformation matrix between the first bone pose and the target bone pose;

[0127] Based on the pose transformation matrix, extracting the corrected surface model from the coordinate space;

[0128] Overlaying the extracted corrected surface model and the target bone skinning model to generate the animated character.

[0129] In this embodiment, the pre-produced reference surface model and exemplar surface model are in the same coordinate space, and the corrected surface model is obtained by fusing the reference surface model and the exemplar surface model. Therefore, the corrected surface model is also in this coordinate space. Obtaining a pose transformation matrix between the first bone pose and the target bone pose; then, based on the pose transformation matrix, extracting the corrected surface model from the coordinate space; and then overlaying the extracted corrected surface model and the target bone skinning model to generate the corresponding animated character.

[0130] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0131] In one embodiment, before superimposing the extracted corrected surface model on the target bone skinned model to generate the animated character, it further includes: performing additional surface deformation on the target bone skinned model.

[0132] Superimposing the extracted corrected surface model on the target bone skinned model to generate the animated character includes: superimposing the extracted corrected surface model on the target bone skinned model that has undergone additional surface deformation to generate the animated character.

[0133] In this embodiment, after skinning the reference surface model based on the target bone pose to generate the target bone skinned model, additional surface deformation is performed on the target bone skinned model. Among them, the additional surface deformation can be generated based on a third-party system. For example: after generating the target bone skinned model, call a third-party muscle simulation system to apply specific-shaped muscles to the target bone skinned model.

[0134] After extracting the fused corrected surface model from the coordinate space where the reference surface model is located, the extracted corrected surface model can be superimposed on the target bone skinned model with additional surface deformation, thereby generating the corresponding animated character.

[0135] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0136] In one embodiment, obtaining the second bone pose of the animated character includes: obtaining at least two second bone poses of the animated character.

[0137] Generating an exemplary surface model of the second bone pose based on the reference surface model and the second bone pose includes: respectively generating exemplary surface models of the at least two second bone poses based on the reference surface model and the at least two second bone poses.

[0138] Obtaining the pose transformation matrix between the first bone pose and the second bone pose includes: obtaining the pose transformation matrices between the first bone pose and the at least two second bone poses respectively.

[0139] Convert the example surface model and the reference surface model to the same coordinate space to call the reference surface model and the example surface model in this coordinate space for generating the animated character, including: converting the at least two example surface models and the reference surface model to the same coordinate space to call the reference surface model and the at least two example surface models in this coordinate space for generating the animated character.

[0140] It can be understood that in the material resource production stage, only one example surface model can be generated, so that the animated character can be generated only based on the reference surface model and one example surface model; or at least two example surface models can be generated, so that the animated character can be generated only based on the reference surface model and at least two example surface models. In this embodiment, in the material resource production stage, at least two example surface models are generated. Specifically, in the material resource production stage, after obtaining at least two second bone postures, for each second bone posture respectively - obtain the corresponding example surface model; obtain the corresponding pose transformation matrix; and convert to the same coordinate space according to the corresponding pose transformation matrix and the reference surface model.

[0141] In one embodiment, calling the reference surface model and the at least two example surface models in this coordinate space for generating the animated character includes:

[0142] Obtain the target bone posture of the animated character;

[0143] Perform skinning processing on the reference surface model based on the target bone posture to obtain the target bone skinning model of the target bone posture;

[0144] Obtain the reference surface model and the at least two example surface models in this coordinate space;

[0145] Based on the reference surface model and the at least two example surface models, obtain the corrected surface model of the target bone posture;

[0146] Generate the animated character based on the target bone skinning model and the corrected surface model.

[0147] In this embodiment, the pre-produced material resources include at least two example surface models. Correspondingly, when generating the corrected surface model according to the pre-produced material resources, the image processing terminal generates the corrected surface model according to at least two example surface models and the reference surface model.

[0148] Specifically, if in the stage of production of material resources, taking the reference surface model M0 in the first bone posture P0 as a reference, an exemplary surface model M1 in a second bone posture P1, an exemplary surface model M2 in a second bone posture P2, and an exemplary surface model M3 in a second bone posture P3 are generated. Then in the stage of generating an animated character, when generating a corrected surface model: it can be determined that the first bone posture P0, the second bone posture P1, the second bone posture P2, and the second bone posture P3 are fused into a target bone posture P, the weight W0 assigned to P0, the weight W1 assigned to P1, the weight W2 assigned to P2, and the weight W3 assigned to P3; and then, according to W0, W1, W2, and W3, M0, M1, M2, and M3 are fused to obtain the corrected surface model M. Among them, according to W0, W1, W2, and W3, fusing M0, M1, M2, and M3 to obtain the corrected surface model M can be carried out in the way of W0*M0 + W1*M1 + W2*M2 + W3*M3 = M.

[0149] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0150] Next, refer to Figure 5 to describe the process in the stage of generating an animated character in an embodiment of the present invention.

[0151] As Figure 5 shown: The pre-produced material resources (all stored in the reference coordinate space) include - the reference surface model M0, the exemplary surface model M1, the exemplary surface model M2, the exemplary surface model M3, and up to the exemplary surface model M i . Correspondingly, the bone postures that can be obtained in advance are - the first bone posture P0 of the reference surface model M0, the second bone posture P1 of the exemplary surface model M1, the second bone posture P2 of the exemplary surface model M2, the second bone posture P3 of the exemplary surface model M3, and up to the second bone posture Pi of the exemplary surface model M i .

[0152] According to the first bone posture P0 and the obtained target bone posture P, calculate the posture transformation matrix between the two, so as to perform coordinate space transformation in the subsequent process through this posture transformation matrix.

[0153] Perform skinning calculation on the reference surface model M0 according to the target bone posture P to obtain a target bone skinning model; and then, on the basis of the target bone skinning model, apply additional surface deformation by a third-party system (for example: apply specific-shaped muscles by a third-party muscle simulation system).

[0154] Reading Skeletal Postures - Reading the first skeletal posture P0, the second skeletal postures P1, P2, P3, up to the second skeletal posture P i ; Apply the RBF (Radial Basis Function) algorithm to interpolate between the read skeletal postures, so as to obtain the weights that need to be assigned to each read skeletal posture in order to fuse the read skeletal postures into the target skeletal posture P; and then, according to the assigned weights, fuse the corresponding surface models of each read skeletal posture accordingly to obtain the corrected surface model stored in the reference coordinate space.

[0155] Apply the pose transformation matrix to perform coordinate transformation on the corrected surface model stored in the reference coordinate space, extract it from the reference coordinate space, and then superimpose it on the target skeletal skin model that has been skinned and applied with additional surface deformation, thereby generating the corresponding animated character.

[0156] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and scope of use of the present invention.

[0157] Figure 6 Shows the terminal interface diagram of applying this image processing method to Maya software (a 3D modeling software) for animation generation in an embodiment of the present invention.

[0158] In this embodiment, the pre-produced material resources are the upper arm surface models of various skeletal postures generated for the upper arm of the animated character. The terminal interface diagram of Maya software shown in this embodiment includes four nodes integrated with corresponding functions: the upper arm posture reading node (uperarm_r node), the skinning node (skinCluster node), the additional surface deformation node (deformate node), and the fusion node (posedriver node). Among them, the uperarm_r node is mainly used to read the upper arm surface models of various skeletal postures in the material resources; the shinCluster node is mainly used for skinning; the deformate node is mainly used for applying additional surface deformation; the posedriver node is mainly used for fusing the surface models to generate the corrected surface model. Among them, the calculation and application of the pose transformation matrix can be encapsulated in the posedriver node.

[0159] In the prior art, since the produced material resources cannot support the compatibility with complex non-linear surface deformations during the animation character generation stage, therefore, the skinCluster node used for skinning during the animation character generation stage can only be placed behind the posedriver node mainly used for surface model fusion; moreover, in the prior art, the deformate node used to apply additional surface deformations cannot be directly placed between the skinCluster node and the posedriver node. According to the image processing method provided by the embodiments of the present invention, the corrected surface model obtained by the posedriver node can be compatible with any non-linear surface deformation, so that after applying the pose transformation matrix, it can be directly superimposed on the bone skin model that has been skinned and additional surface deformations have been applied.

[0160] It should be noted that this embodiment is only an exemplary illustration and should not limit the functions and usage scope of the present invention.

[0161] According to an embodiment of the present invention, as Figure 7 shown, there is also provided an image processing apparatus, including:

[0162] A first acquisition module 510, configured to acquire a reference surface model of the first bone pose of the animation character;

[0163] A second acquisition module 520, configured to acquire the second bone pose of the animation character;

[0164] A generation module 530, configured to generate an example surface model of the second bone pose based on the reference surface model and the second bone pose;

[0165] A third acquisition module 540, configured to acquire a pose transformation matrix between the first bone pose and the second bone pose;

[0166] A storage module 550, configured to convert the example surface model and the reference surface model to the same coordinate space based on the pose transformation matrix, so as to call the reference surface model and the example surface model in the coordinate space for the generation of the animation character.

[0167] In an exemplary embodiment of the present invention, the generation module 530 is configured to:

[0168] Perform skinning on the reference surface model based on the second bone pose to obtain an example bone skin model of the second bone pose;

[0169] Extract the surface data of the example bone skin model, and generate an example surface model of the second bone pose according to the surface data.

[0170] In an exemplary embodiment of the present invention, the device is configured to:

[0171] Obtain a modification request from a requester for the exemplary skeletal skinning model;

[0172] If the verification of the modification request passes, open the modification permission of the exemplary skeletal skinning model to the requester, so that the requester can modify the exemplary skeletal skinning model;

[0173] Extract the surface data of the modified exemplary skeletal skinning model.

[0174] In an exemplary embodiment of the present invention, the storage module 550 is configured to: use the pose transformation matrix to perform coordinate transformation processing on the exemplary surface model, and store the exemplary surface model in the coordinate space where the reference surface model is located.

[0175] In an exemplary embodiment of the present invention, the device is configured to:

[0176] Obtain the target bone pose of the animated character;

[0177] Perform skinning processing on the reference surface model based on the target bone pose to obtain the target bone skinning model of the target bone pose;

[0178] Obtain the reference surface model and the exemplary surface model in the coordinate space;

[0179] Obtain the corrected surface model of the target bone pose based on the reference surface model and the exemplary surface model;

[0180] Generate the animated character based on the target bone skinning model and the corrected surface model.

[0181] In an exemplary embodiment of the present invention, the device is configured to:

[0182] Obtain the first bone pose corresponding to the reference surface model and the second bone pose corresponding to the exemplary surface model;

[0183] According to the target bone pose, determine the weights assigned to the first bone pose and the second bone pose respectively when the first bone pose and the second bone pose are fused into the target bone pose;

[0184] Fuse the reference surface model and the exemplary surface model based on the weights to obtain the corrected surface model.

[0185] In an exemplary embodiment of the present invention, the device is configured to:

[0186] Obtain a pose transformation matrix between the first bone pose and the target bone pose;

[0187] Based on the pose transformation matrix, extract the corrected surface model from the coordinate space;

[0188] Overlay the extracted corrected surface model with the target bone skinning model to generate the animated character.

[0189] In an exemplary embodiment of the present invention, the device is configured to:

[0190] Perform additional surface deformation on the target bone skinning model;

[0191] Overlay the extracted corrected surface model with the target bone skinning model that has undergone additional surface deformation to generate the animated character.

[0192] In an exemplary embodiment of the present invention, the device is configured to:

[0193] Obtain at least two second bone poses of the animated character;

[0194] Based on the reference surface model and the at least two second bone poses, respectively generate exemplary surface models of the at least two second bone poses;

[0195] Obtain pose transformation matrices between the first bone pose and the at least two second bone poses respectively;

[0196] Convert the at least two exemplary surface models and the reference surface model to the same coordinate space to call the reference surface model and the at least two exemplary surface models in the coordinate space for generating the animated character.

[0197] In an exemplary embodiment of the present invention, the device is configured to:

[0198] Obtain the target bone pose of the animated character;

[0199] Based on the target bone pose, perform skinning on the reference surface model to obtain a target bone skinning model of the target bone pose;

[0200] Obtain the reference surface model and the at least two exemplary surface models in the coordinate space;

[0201] Based on the reference surface model and the at least two exemplary surface models, obtain a corrected surface model of the target bone pose;

[0202] Generate the animated character based on the target skeletal skinning model and the corrected surface model.

[0203] In an exemplary embodiment of the present invention, the device is configured to:

[0204] Obtain manipulation data input based on an input device;

[0205] Based on the manipulation data, obtain the target skeletal pose of the animated character.

[0206] In an exemplary embodiment of the present invention, the device is configured to:

[0207] Obtain sensor data input based on a sensor device;

[0208] Based on the sensor data, capture the user's actions;

[0209] Based on the user's actions, obtain the target skeletal pose of the animated character.

[0210] Next, refer to Figure 8 to describe the image processing electronic device 60 according to an embodiment of the present invention. Figure 8 The image processing electronic device 60 shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present invention.

[0211] As Figure 8 shown, the image processing electronic device 60 is presented in the form of a general-purpose computing device. The components of the image processing electronic device 60 may include, but are not limited to: at least one of the above-mentioned processing units 610, at least one of the above-mentioned storage units 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).

[0212] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the description part of the above-mentioned exemplary methods in this specification. For example, the processing unit 610 can execute the steps as shown in Figure 3 shown.

[0213] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0214] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0215] The bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0216] The image processing electronic device 60 may also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and may also communicate with one or more devices that enable a user to interact with the image processing electronic device 60, and / or communicate with any device that enables the image processing electronic device 60 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 650. The input / output (I / O) interface 650 is connected to the display unit 640. Moreover, the image processing electronic device 60 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. As shown in the figure, the network adapter 660 communicates with other modules of the image processing electronic device 60 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the image processing electronic device 60, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0217] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0218] In an exemplary embodiment of the present invention, there is also provided a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the method described in the method embodiment part above.

[0219] According to an embodiment of the present invention, there is also provided a program product for implementing the method in the above method embodiment. It may be a portable compact disc read-only memory (CD-ROM), include program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0220] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RGM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0221] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, and this readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0222] The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0223] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as JAVA, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (KGN) or a wide area network (WGN), or it can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0224] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0225] In addition, although the steps of the method in the present invention are described in a specific order in the drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution, etc.

[0226] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0227] Other embodiments of the present invention will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following the general principles of the invention and including known common general knowledge or conventional technical means in the technical field not disclosed in the present invention. The specification and examples are only regarded as exemplary, and the true scope and spirit of the invention are pointed out by the appended claims.

Claims

1. An image processing method, characterized in that, The method includes: Obtaining a reference surface model of the first skeletal pose of the animated character; Obtaining the second skeletal pose of the animated character; Generating an exemplary surface model of the second skeletal pose based on the reference surface model and the second skeletal pose; Obtaining a pose transformation matrix according to the first skeletal pose and the second skeletal pose; Based on the pose transformation matrix, converting the exemplary surface model and the reference surface model to the same coordinate space to call the reference surface model and the exemplary surface model in the coordinate space for generating the animated character; Wherein, calling the reference surface model and the exemplary surface model in the coordinate space for generating the animated character includes: Obtaining the target skeletal pose of the animated character; Performing skinning processing on the reference surface model based on the target skeletal pose to obtain a target skeletal skinning model of the target skeletal pose; Obtaining the reference surface model and the exemplary surface model in the coordinate space; Obtaining a corrected surface model of the target skeletal pose based on the reference surface model and the exemplary surface model; Generating the animated character based on the target skeletal skinning model and the corrected surface model.

2. The method according to claim 1, wherein Generating the exemplary surface model of the second skeletal pose based on the reference surface model and the second skeletal pose includes: Performing skinning processing on the reference surface model based on the second skeletal pose to obtain an exemplary skeletal skinning model of the second skeletal pose; Extracting surface data of the exemplary skeletal skinning model and generating an exemplary surface model of the second skeletal pose according to the surface data.

3. The method according to claim 2, characterized in that, Before extracting the surface data of the exemplary skeletal skinning model, the method further includes: Obtaining a modification request of the requestor for the exemplary skeletal skinning model; If the verification of the modification request passes, opening the modification permission of the exemplary skeletal skinning model to the requestor so that the requestor can modify the exemplary skeletal skinning model; Extracting the surface data of the exemplary skeletal skinning model includes: extracting the surface data of the modified exemplary skeletal skinning model.

4. The method according to claim 1, characterized in that Based on the pose transformation matrix, converting the exemplary surface model and the reference surface model to the same coordinate space includes: using the pose transformation matrix to perform coordinate transformation processing on the exemplary surface model and storing the exemplary surface model in the coordinate space where the reference surface model is located.

5. The method according to claim 1, wherein Obtaining the corrected surface model of the target skeletal pose based on the reference surface model and the exemplary surface model includes: Obtaining the first skeletal pose corresponding to the reference surface model and the second skeletal pose corresponding to the exemplary surface model; Determining the weights assigned to the first skeletal pose and the second skeletal pose respectively when fusing the first skeletal pose and the second skeletal pose into the target skeletal pose; Fusing the reference surface model and the exemplary surface model based on the weights to obtain the corrected surface model.

6. The method according to claim 1, wherein Generating the animated character based on the target skeletal skinning model and the corrected surface model includes: Obtain the pose transformation matrix between the first bone pose and the target bone pose; Extract the corrected surface model from the coordinate space based on the pose transformation matrix; Superimpose the extracted corrected surface model and the target bone skinning model to generate the animated character.

7. The method according to claim 6, wherein Before superimposing the extracted corrected surface model and the target bone skinning model to generate the animated character, the method further includes: performing additional surface deformation on the target bone skinning model; Superimposing the extracted corrected surface model and the target bone skinning model to generate the animated character includes: superimposing the extracted corrected surface model and the target bone skinning model that has undergone additional surface deformation to generate the animated character.

8. The method according to claim 1, characterized in that, Obtain the target bone pose of the animated character, including: Obtain the control data input based on the input device; Based on the control data, obtain the target bone pose of the animated character.

9. The method according to claim 1, wherein Obtain the target bone pose of the animated character, including: Obtain the sensor data input based on the sensor device; Based on the sensor data, capture the user action; Based on the user action, obtain the target bone pose of the animated character.

10. The method according to claim 1, characterized in that, Obtain the second bone pose of the animated character, including: obtaining at least two second bone poses of the animated character; Generate the exemplary surface model of the second bone pose based on the reference surface model and the second bone pose, including: generating the exemplary surface models of the at least two second bone poses respectively based on the reference surface model and the at least two second bone poses; Obtain the pose transformation matrix according to the first bone pose and the second bone pose, including: obtaining the pose transformation matrices between the first bone pose and the at least two second bone poses respectively; Convert the exemplary surface model and the reference surface model to the same coordinate space to call the reference surface model and the exemplary surface model in the coordinate space for generating the animated character, including: converting the at least two exemplary surface models and the reference surface model to the same coordinate space to call the reference surface model and the at least two exemplary surface models in the coordinate space for generating the animated character.

11. The method according to claim 10, wherein Calling the reference surface model and the at least two exemplary surface models in the coordinate space for generating the animated character, including: Obtain the target bone pose of the animated character; Perform skinning on the reference surface model based on the target bone pose to obtain the target bone skinning model of the target bone pose; Obtain the reference surface model and the at least two exemplary surface models in the coordinate space; Obtain the corrected surface model of the target bone pose based on the reference surface model and the at least two exemplary surface models; Generate the animated character based on the target bone skinning model and the corrected surface model.

12. An image processing apparatus, characterized in that, The device includes: The first acquisition module is configured to acquire the reference surface model of the first bone pose of the animated character; A second acquisition module configured to acquire a second bone pose of the animated character; A generation module configured to generate an exemplary surface model of the second bone pose based on the reference surface model and the second bone pose; A third acquisition module configured to obtain a pose transformation matrix according to the first bone pose and the second bone pose; A storage module configured to, based on the pose transformation matrix, transform the exemplary surface model and the reference surface model into the same coordinate space, so as to call the reference surface model and the exemplary surface model in the coordinate space to generate the animated character; The apparatus is configured to: Acquire a target bone pose of the animated character; Perform skinning processing on the reference surface model based on the target bone pose to obtain a target bone skinning model of the target bone pose; Acquire the reference surface model and the exemplary surface model in the coordinate space; Obtain a corrected surface model of the target bone pose based on the reference surface model and the exemplary surface model; Generate the animated character based on the target bone skinning model and the corrected surface model.

13. An image processing electronic device, characterized in that, Including: A memory storing computer-readable instructions; A processor that reads the computer-readable instructions stored in the memory to execute the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, Stored thereon are computer-readable instructions which, when executed by a processor of a computer, cause the computer to execute the method according to any one of claims 1-11.

Images