Video image generation method, system, apparatus

Abstract

This disclosure provides a video image generation method, system, and apparatus, relating to the field of data processing, which can improve the problem of low user engagement. The specific technical solution includes: acquiring an initial video clip; modeling a target character in the initial video clip using character parameters input by the user; receiving user motion parameters input via a motion capture device; and, based on the user motion parameters, performing motion control on the modeled target character to generate a target game clip. This disclosure can greatly enhance user engagement in interactive videos experiencing AR, VR, MR, and even XR scenarios, generating videos with user participation and improving the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of data processing, and in particular to a method, system, and apparatus for generating video images. Background Technology

[0002] Currently, Extended Reality (XR) technology is a combination of Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR) technologies. It reconstructs the human-computer interaction paradigm through virtual-real fusion, real-time interaction, and 3D registration capabilities. With the support of XR, VR will enjoy a superior product experience, and XR will make the boundaries between virtual reality and the real world increasingly blurred and seamless.

[0003] However, current deployments of AR and VR in many shopping malls are mostly focused on games, including game content integration and scene experiences. Gaining user acceptance, especially in terms of engagement, across numerous AR, VR, MR, and even XR scenarios still presents many technical challenges. Summary of the Invention

[0004] This disclosure provides a video image generation method, system, and apparatus that can improve the problem of poor user experience due to low user engagement. The technical solution is as follows: According to a first aspect of the present disclosure, a video image generation method is provided, the method comprising: acquiring an initial video segment; modeling a target character in the initial video segment using character parameters input by a user; receiving user motion parameters input by a motion capture device; and performing motion control on the modeled target character based on the user motion parameters to generate a target game segment.

[0005] Based on the above scheme, after obtaining the initial video clip, the target character in the initial video clip is modeled using the character parameters input by the user. The user's motion parameters are received through the motion capture device, and the modeled target character's motion is controlled based on the user's motion parameters to generate the target game clip. This can greatly improve the user's participation in interactive videos in AR, VR, MR, and even XR scenarios, generating videos with user participation and enhancing the user experience.

[0006] In some embodiments, after acquiring the initial video clip, the method further includes: modeling the target environment in the initial video clip based on user-set environmental parameters; the target environment includes, but is not limited to: weather, lighting, background style, and background music.

[0007] In some embodiments, modeling a target person in an initial video clip using user-inputted person parameters includes: If no user number information is entered, replace the user-selected character information in the initial video clip; or if the number of users entered is less than or equal to the number of characters in the initial video clip, replace the user-selected character in the initial video clip; or if the number of users entered is greater than the number of characters in the initial video clip, replace all characters in the initial video clip; model the target characters in the initial video clip using character parameters.

[0008] In some embodiments, obtaining an initial video segment includes: deploying a first initial video resource, the first initial video resource including at least one video segment; playing and training to extract target elements from the first initial video resource; if the target elements are extracted correctly, sorting the first initial video resource according to a preset classification to obtain a second initial video resource; and selecting an initial video segment from the second initial video resource, the initial video segment belonging to the second initial video resource.

[0009] In some embodiments, the method further includes creating the first initial video resource before deploying the first initial video resource.

[0010] In some embodiments, after generating the target game segment, the method further includes: acquiring the target game segment; when the target game segment is deleted, recording modification points and accumulating data for system modeling; when the target game segment is not deleted, temporarily storing the target game segment in the user selection area; when the target game segment in the user selection area is selected by other users and video image generation is completed, increasing the user's video score; when the score exceeds a first preset threshold, synchronizing the target game segment to other system terminals; when the score is lower than a second preset threshold, clearing the target game segment.

[0011] In some embodiments, after generating the target game fragment, the method further includes: modifying the target game fragment based on target parameters input by the user.

[0012] In some embodiments, user action parameters include action parameters, gesture parameters, and virtual weapon operation parameters.

[0013] According to a second aspect of the present disclosure, a video image generation apparatus is provided, including a memory and a processor. The memory has a stored program. When the program is executed in the processor, the processor is used to perform the methods of the first aspect and any embodiment of the first aspect.

[0014] Based on the aforementioned equipment, after acquiring an initial video clip, the target character in the initial video clip is modeled using the character parameters input by the user. The user's motion parameters are received through a motion capture device, and the modeled target character's motion is controlled based on the user's motion parameters to generate the target game clip. This allows users to greatly increase their participation in interactive videos experiencing AR, VR, MR, and even XR scenarios, generating videos with a sense of user participation and enhancing the user experience.

[0015] According to a third aspect of the present disclosure, a video image generation apparatus is provided, comprising: a first acquisition module for acquiring an initial video segment; a modeling module for modeling a target character in the initial video segment using character parameters input by a user; a receiving module for receiving user motion parameters input through a motion capture device; and a generation module for performing motion control on the modeled target character based on the user motion parameters to generate a target game segment.

[0016] In some embodiments, the modeling module is further configured to: model the target environment in the initial video clip based on user-defined environmental parameters; the target environment includes, but is not limited to: weather, lighting, background style, and background music.

[0017] In some embodiments, the modeling module specifically includes: a replacement submodule, used to replace the user-selected character information in the initial video clip when no user quantity information is input; or to replace the user-selected character in the initial video clip when the input user quantity is less than or equal to the number of characters in the initial video clip; or to replace all characters in the initial video clip when the input user quantity is greater than the number of characters in the initial video clip; and a modeling submodule, used to model the target character in the initial video clip using character parameters.

[0018] In some embodiments, the first acquisition module specifically includes: a deployment submodule for deploying a first initial video resource, the first initial video resource including at least one video segment; a playback training submodule for playing and training to extract target elements from the first initial video resource; a sorting submodule for sorting the first initial video resource according to a preset classification to obtain a second initial video resource if the target elements are extracted correctly; and a selection submodule for selecting an initial video segment from the second initial video resource, the initial video segment belonging to the second initial video resource.

[0019] In some embodiments, the first acquisition module further includes a production submodule for producing a first initial video resource.

[0020] In some embodiments, the device further includes: a second acquisition module for acquiring a target game segment; a recording and accumulation module for recording modification points and accumulating data for system modeling when the target game segment is deleted; a temporary storage module for temporarily storing the target game segment in the user selection area when the target game segment is not deleted; an addition module for adding user video points when the target game segment in the user selection area is selected by other users and video image generation is completed; a synchronization module for synchronizing the target game segment to other system terminals when the points exceed a first preset threshold; and a cleanup module for cleaning up the target game segment when the points fall below a second preset threshold.

[0021] In some embodiments, the apparatus further includes a modification module for modifying a target game segment based on target parameters input by a user.

[0022] In some embodiments, user action parameters include action parameters, gesture parameters, and virtual weapon operation parameters.

[0023] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, characterized in that the computer program storage medium has program instructions that, when executed by a processor, cause the processor to perform the method of the first aspect and any embodiment of the first aspect.

[0024] According to a fifth aspect of the present disclosure, a chip system is provided, characterized in that the chip system includes at least one processor, which, when program instructions are executed in the at least one processor, causes the at least one processor to perform the method of the first aspect and any embodiment of the first aspect.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0027] Figure 1 This is a schematic diagram of the overall structure 100 of a video image generation system provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of a video image generation method 200 provided in an embodiment of this disclosure; Figure 3 This is a flowchart of a video resource provision method 300 provided in an embodiment of this disclosure; Figure 4 This is a flowchart of a video resource synthesis method 400 provided in an embodiment of this disclosure; Figure 5 This is a flowchart of a video microprocessing method 500 provided in an embodiment of this disclosure; Figure 6 This is a structural diagram of a video image generation device 600 provided in an embodiment of this disclosure; Figure 7 This is a structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure; Figure 8 This is another structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure; Figure 9 This is another structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure; Figure 10 This is another structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure; Figure 11 This is another structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure; Figure 12 This is another structural diagram of a video image generation apparatus 700 provided in an embodiment of this disclosure. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0029] With the rapid development of Virtual Reality (VR) devices, VR devices have been increasingly accepted and recognized. However, high-quality VR devices are expensive, and the pace of updates exceeds the affordability of ordinary consumers, affecting the speed of VR device adoption. The demand for VR devices is most commonly seen in gaming, due to the unique appeal of games. VR devices replace the two-dimensional limitations of traditional screen displays with three-dimensional spatial vision and human tactile interaction, transforming gamers from "observers" to "immersers." The high refresh rate and low latency of VR devices greatly improve game smoothness. However, the lack of consistency in 5G spectrum networks limits the efficient data transmission and large-scale application of VR devices to some extent. Augmented Reality (AR) is a technology that overlays virtual information onto the real world. Through cameras, sensors, and real-time computing, it allows virtual objects to seamlessly blend with the real environment, achieving an interactive experience. Unlike VR (completely virtual) and Mixed Reality (MR) (real-time interaction between virtual and reality), AR emphasizes the combination of virtual and real, enhancing the real-world experience. Extended Reality (XR) technology is a combination of Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR) technologies. It reconstructs the human-computer interaction paradigm through virtual-real fusion, real-time interaction, and 3D registration capabilities. With the support of XR, VR experiences a superior product experience, and the boundaries between virtual reality and the real world become increasingly blurred and imperceptible.

[0030] However, current deployments of AR and VR in many shopping malls are mostly focused on games, with game content and scene experiences being integrated. Gaining user acceptance, especially in terms of engagement, across numerous AR, VR, MR, and even XR scenarios still presents many technical challenges.

[0031] In view of this, the present disclosure provides a video image generation method that can improve the above-mentioned problems and enhance the user experience.

[0032] To better understand the method provided in the embodiments of this disclosure, the system architecture involved in the method will be introduced first.

[0033] Figure 1 This is a schematic diagram of the overall structure 100 of a video image generation system provided in an embodiment of this disclosure. For example... Figure 1 As shown, the overall structure of the system includes an adversarial XR game video resource management module, a set of XR-supporting physical devices, an adversarial XR game operation module, an adversarial XR game video modeling and compositing module, and program products connecting the above modules.

[0034] It should be understood that the following methods provided in this embodiment are applicable to Figure 1 The diagram shows the overall structure of the system and the various modules within the framework.

[0035] This disclosure provides a video image generation method 200, such as... Figure 2 As shown, the video image generation method 200 includes the following steps: S210, Obtain the initial video clip.

[0036] Specifically, the initial video clip can be obtained through the following steps: Deploy a first initial video resource, which includes at least one video segment; Play and train to extract target elements from the first initial video resource; If the target elements are extracted correctly, the first initial video resources are sorted according to the preset classification to obtain the second initial video resources; The initial video segment is obtained by selecting the second initial video resource, and the initial video segment belongs to the second initial video resource.

[0037] For example, the adversarial XR game video resource (i.e., the first initial video resource) can be deployed first, which contains at least one video clip. Then, the system plays the first initial video resource and trains the extraction of elements such as items related to the video characters (i.e., target elements). If the target elements are extracted correctly, the first initial video resource is sorted according to a preset classification to obtain the second initial video resource. If the target elements are extracted incorrectly, the video resource is temporarily filtered and reported to the system maintenance personnel for analysis and resolution.

[0038] The video resources of the adversarial XR game video generation system, namely the set of video clips used as the initial reference for system creation, first need to be edited from clips of exciting videos. Multiple exciting clips from different time periods can be extracted from the same video and deployed and uploaded to the resource storage management module of the adversarial XR game video generation system.

[0039] The shopping mall's competitive XR game scene provider is responsible for deploying and updating pre-edited sets of fight scene videos for participants to choose from. Upon receiving updated or deleted videos, the competitive XR game system reorders the videos by category.

[0040] Competitive XR games can offer categories of competitive fighting games, such as ancient martial arts, ancient mythology, modern fighting, science fiction fighting, fantasy fighting, realistic fighting, comedic fighting, historical war fighting, opera fighting, and anime fighting. Users can choose at least one person and a scene to fight and recreate the fighting scene, reshape the fighting result, and choose the number of people and the fighting targets. All fighting scenes only show the fighting posture and the fighting result, and blood and violence are restricted.

[0041] Optionally, before deploying the first initial video resource, the method may further include: Create the first initial video resource.

[0042] For example, adversarial XR game video assets (i.e., the first initial video asset) can be created.

[0043] Based on the above scheme, as an example, Figure 3 This is a flowchart of a video resource provision method 300 provided in this embodiment of the present disclosure, applicable to the above embodiments.

[0044] S220 models the target person in the initial video clip using the person parameters input by the user.

[0045] Specifically, this can be achieved through the following steps: If no user quantity information is entered, replace the user-selected role information in the initial video clip; or If the number of users entered is less than or equal to the number of characters in the initial video clip, replace the characters selected by the users in the initial video clip; or If the number of users entered exceeds the number of characters in the initial video clip, replace all characters in the initial video clip; The target person in the initial video clip is modeled using person parameters.

[0046] For example, a user can select elements such as characters, weapons, clothing, and appearance in an initial video clip. The system then checks if it's a real-person team: if the user hasn't entered the number of users (i.e., not a real-person team), the selected characters in the source video (i.e., the initial video clip) are replaced; if the number of users entered is less than or equal to the number of characters in the initial video clip, the selected characters are replaced; if the number of users entered is greater than the number of characters in the initial video clip, all characters in the initial video clip are replaced. Next, the system retrieves the character parameters set by the user and models the target characters in the initial video clip using these parameters.

[0047] For example, in a competitive XR game video generation system, game participants (i.e., users) can use various terminals within the system; that is, a single system can have multiple terminal devices available for different game participants to use simultaneously. Participants can play in teams or solo. Through some pre-selection options by the game participants, such as the selected video character, corresponding weapon and clothing style, whether height and weight are based on the game participant themselves, or inputting height and weight parameters for modeling, minor modifications and reprocessing of the video are also possible later. After determining the task to be replaced in the source video (i.e., the initial video clip), static modeling is performed using the game participant's (i.e., real person's) body parameters or custom body parameters, style, weapons, hairstyle, and clothing parameters. Based on the competitive XR combat result selected by the game participant and the above parameters, pre-modeling of the video is performed to generate a new video clip.

[0048] It should be understood that in the above scheme, after participants in the adversarial XR game select their combat opponent, they are matched with real people on-site for video reconstruction. That is, the real person in the combat video is replaced with a person from the original video in the captured video for focused reconstruction. The person in the original video replaced by the real person is referred to as the pre-replaced person. The more real participants in the adversarial XR game, the greater the difficulty and time required for video reconstruction.

[0049] If at least one real person participates in a two-player adversarial XR game, the system will model the game participants and replace the selected person in the source video with the model based on their height, weight and facial image. Other people will be based on the person in the source video.

[0050] The hairstyle, clothing, weapons, height, and weight of the real person relative to the modeled avatar can be adjusted. The model can default to the height and weight of the person in the source video, only modifying the avatar's hairstyle and clothing. Alternatively, when selecting a person, the height and weight can be reshaped according to the actual height and weight of the real person or according to the real person's own settings, including but not limited to height, weight, avatar, hairstyle, clothing, weapons, and even parameters such as weather, background, and lighting.

[0051] S230 receives user motion parameters input through the motion capture device.

[0052] For example, user motion parameters can be received via motion capture devices. These devices include, but are not limited to: XR controllers, wristbands / bracelets / finger tracking sensors, head tracking sensors, full-body motion capture suits, and inertial motion capture sensors. User motion parameters include motion parameters, gesture parameters, and operational parameters of the virtual weapon.

[0053] S240, based on user action parameters, performs motion control on the modeled target character to generate the target game segment.

[0054] For example, based on an initial video clip after modeling, a user can begin fighting in a combat-oriented XR game. The system terminal can collect the user's movements and gestures, as well as parameters such as the trajectory, speed, and force of virtual weapons, to control the movements of the modeled target character and generate the target game clip.

[0055] For example, once all participants in a competitive XR game are ready and the fight begins, the system terminals can collect parameters such as the actions, gestures, and how virtual weapons are held or placed, as well as the trajectory, speed, and force of movement of the game participants in front of the terminals (i.e., motion parameters). The system can then control the actions of the modeled target character to generate the target game segment.

[0056] After a certain period of combat in a competitive XR game, the system terminal can output a video of the entire combat process for the game participants.

[0057] It should be understood that in the above scheme, real people can train the adversarial XR game video generation system through repeated games, such as changes in movements and intensity, and finally generate videos after multiple training sessions. At the same time, the videos can be previewed at different time points for users to choose from, forming the final video.

[0058] When a competitive XR game begins, real people can first watch the source video and recreate the competitive fight scene in the source video by changing their body gestures. They can choose to imitate or customize. If they choose to imitate, the video remodeling will try to imitate the action scenes in the source video as much as possible. If they choose to customize, the XR game video generation system will capture the real person's movements and expressions, the speed and intensity of the competitive fight, and add parameters such as the real person's chosen clothing and facial expressions to recreate the model. The remodel will then replace the character with a new action scene and not replace the character in the source video, together to complete a new competitive XR fight.

[0059] Optionally, after acquiring the initial video segment, the method may further include: The target environment in the initial video clip is modeled based on the user-defined environmental parameters.

[0060] The target environment includes, but is not limited to: weather, lighting, background style, and background music.

[0061] As an example, environmental parameters can include, but are not limited to, information such as weather, lighting, background, and artificial light, and can also include information about the outcome of the fight. Furthermore, the target environment in the initial video clip can be modeled based on the user-defined environmental parameters.

[0062] For example, in a competitive XR game video generation system, game participants (i.e., users) can use various terminals of the system simultaneously. A single system can have multiple terminal devices available for different game participants. Participants can play in teams or solo. Static modeling is performed based on some of the game participants' pre-selected options, such as weather, background, and lighting parameters. Then, video pre-modeling is performed based on the competitive XR combat results selected by the game participants and the aforementioned parameters to generate new video clips.

[0063] Based on the above scheme, as an example, Figure 4 This is a flowchart of a video resource synthesis method 400 provided in this embodiment, applicable to the above embodiments.

[0064] Optionally, after generating the target game fragment, the method may further include: Based on the target parameters input by the user, the target game segment is modified to generate the modified target game segment.

[0065] For example, after the game ends, if the author is not satisfied with the generated video (i.e., the target game segment), they can modify the fighting details in the video (i.e., input the target parameters) and form the final video (i.e., the modified target game segment).

[0066] For example, game participants can watch videos (i.e., target game clips) and modify certain time periods or parts of the fight details. They can input target parameters to modify previously preset parameters, or even change the outcome of the fight, thereby generating more personalized target game clips.

[0067] Optionally, after generating the target game fragment, the method may further include: Obtain the target game segment; When a target game segment is deleted, the modification points are recorded and data for system modeling is accumulated; If the target game segment has not been deleted, the target game segment will be temporarily stored in the user selection area; When the target game segment in the user selection area is selected by another user and a video image is generated, the user's video score is increased; When the score exceeds the first preset threshold, the target game segment will be synchronized to other system terminals; When the score falls below the second preset threshold, the target game segment is cleared.

[0068] For example, after the system generates at least one target game segment or a modified target game segment, the target game segment or the modified target game segment can be obtained through tools such as Bluetooth, WeChat, or USB flash drive. Taking the acquisition of the target game segment as an example, if the target game segment is deleted at this time, the video is cleared, the modification points are recorded, and data for service system modeling is accumulated; if the target game segment is not deleted, the target game segment is temporarily stored in the user selection area. Subsequently, when the target game segment in the user selection area is selected by other users and a video image is generated, the user's video score is increased. When the score exceeds a first preset threshold, the target game segment is synchronized to other system terminals; when the score is lower than a second preset threshold, the target game segment is cleared.

[0069] For example, after each participant completes a competitive XR game on the system terminal, they can obtain a video of their chosen winning outcome (i.e., the target game segment). Participants can choose to win themselves or someone else. After modifying elements such as weather, body parameters, appearance, background, and lighting in the video, an updated video (i.e., the modified target game segment) is generated. Multiple pre-saved videos generated by the system are available for participants to view. Once all videos have been processed, participants can retrieve the desired video via Bluetooth, WeChat, or a USB drive, either individually or in multiple formats. The final video selection allows participants to either save and share the video or delete it. If a video is deleted, the system terminal will clean it up and record the modification points throughout the video processing, while accumulating data for reference in the modeling of the adversarial XR game system. If a video is retained, it will first be deployed to a temporary user video area for other game participants to choose as a reference video. If other user participants choose and complete their own video production, the user video will accumulate points. When the points exceed the first threshold, the video can enter the system terminal's video resource area, sorted by category and update date, for other system terminal users to choose from. If the accumulated points of a user video do not reach the second threshold within a certain period, the video will be deleted.

[0070] In addition, the system can also allow users to access video clips via the internet or USB drives. The system needs to extract elements such as character movements from the videos and remind users that a certain amount of time is required. Alternatively, it can use an on-demand model, allowing users to recreate the video at a specific time, such as half an hour or an hour later. The system can then use existing video resources to generate adversarial XR game videos. This necessitates adding a backend processing program for user video resource extraction, modeling, and execution.

[0071] Based on the above scheme, as an example, Figure 5 This is a flowchart of a video microprocessing method 500 provided in this disclosure embodiment, applicable to the above embodiment.

[0072] Based on the above scheme, the method provided in this disclosure first obtains an initial video segment and then models the target character in the initial video segment using the character parameters input by the user. It receives user motion parameters input through a motion capture device and performs motion control on the modeled target character based on the user motion parameters to generate a target game segment. This can greatly improve the user's participation in interactive videos of AR, VR, MR, and even XR scenarios, generate videos with user participation, and enhance the user experience.

[0073] Based on the above Figure 2 The video image generation method described in the corresponding embodiments is described below as an embodiment of the apparatus of this disclosure, which can be used to execute the method embodiments of this disclosure.

[0074] This disclosure provides a video image generation device 600, such as... Figure 6 As shown. The video image generation device 600 includes: a memory 601 and a processor 602.

[0075] The memory 601 is used to store the program.

[0076] When the program is executed in processor 602, processor 602 is used to execute the video image generation method described above.

[0077] The processor 602 is used to: acquire an initial video clip; model a target character in the initial video clip using character parameters input by the user; receive user motion parameters input through a motion capture device; and perform motion control on the modeled target character based on the user motion parameters to generate a target game clip.

[0078] Optionally, the processor 602 is also used to model the target environment in the initial video clip based on user-set environmental parameters; the target environment includes, but is not limited to, weather, lighting, background style, and background music.

[0079] Optionally, the processor 602 is specifically used to: replace the user-selected character information in the initial video clip when no user quantity information is input; or replace the user-selected character in the initial video clip when the input user quantity is less than or equal to the number of characters in the initial video clip; or replace all characters in the initial video clip when the input user quantity is greater than the number of characters in the initial video clip; and model the target character in the initial video clip using character parameters.

[0080] Optionally, the processor 602 is specifically configured to: deploy a first initial video resource, the first initial video resource including at least one video segment; play and train to extract target elements from the first initial video resource; if the target elements are extracted correctly, sort the first initial video resource according to a preset classification to obtain a second initial video resource; and select and obtain an initial video segment through the second initial video resource, the initial video segment belonging to the second initial video resource.

[0081] Optionally, the processor 602 is also used to create a first initial video resource.

[0082] Optionally, the processor 602 is further configured to: acquire a target game segment; when the target game segment is deleted, record the modification points and accumulate data for system modeling; when the target game segment is not deleted, temporarily store the target game segment in the user selection area; when the target game segment in the user selection area is selected by other users and video image generation is completed, increase the user's video score; when the score exceeds a first preset threshold, synchronize the target game segment to other system terminals; when the score is lower than a second preset threshold, clear the target game segment.

[0083] Optionally, the processor 602 is also used to modify the target game segment based on target parameters input by the user.

[0084] Optionally, user action parameters include action parameters, gesture parameters, and virtual weapon operation parameters.

[0085] The video image generation device provided in this embodiment acquires an initial video segment and models the target character in the initial video segment using character parameters input by the user. It receives user motion parameters input through a motion capture device and performs motion control on the modeled target character based on the user motion parameters to generate a target game segment. This greatly enhances user participation in interactive videos of AR, VR, MR, and even XR scenarios, generating videos with user engagement and improving the user experience.

[0086] Based on the above Figure 2 The video image generation method described in the corresponding embodiments is described below as an embodiment of the apparatus of this disclosure, which can be used to execute the method embodiments of this disclosure.

[0087] Based on the above Figure 2 The corresponding embodiment describes a video image generation method. This disclosure also provides a video image generation apparatus 700, such as... Figure 7 As shown.

[0088] The video image generation apparatus 700 includes: The first acquisition module 701 is used to acquire the initial video segment; Modeling module 702 is used to model the target person in the initial video clip based on the person parameters input by the user; The receiving module 703 is used to receive user motion parameters input through the motion capture device; The generation module 704 is used to control the motion of the modeled target character based on user action parameters in order to generate the target game segment.

[0089] Optionally, the modeling module 702 is also used to model the target environment in the initial video clip based on user-set environmental parameters; the target environment includes, but is not limited to, weather, lighting, background style, and background music.

[0090] Optionally, such as Figure 8 As shown, the modeling module 702 specifically includes: The replacement submodule 7021 is used to replace the user-selected role information in the initial video clip when no user quantity information is entered; or to replace the user-selected role in the initial video clip when the number of users entered is less than or equal to the number of roles in the initial video clip; or to replace all roles in the initial video clip when the number of users entered is greater than the number of roles in the initial video clip. Modeling submodule 7022 is used to model the target person in the initial video clip using person parameters.

[0091] Optionally, such as Figure 9 As shown, the first acquisition module 701 specifically includes: Deployment submodule 7011 is used to deploy a first initial video resource, which includes at least one video segment; The playback training submodule 7012 is used to play and train the target elements extracted from the first initial video resource; The sorting submodule 7013 is used to sort the first initial video resource according to a preset classification to obtain the second initial video resource, provided that the target elements are extracted correctly. The selection submodule 7014 is used to select an initial video segment from the second initial video resource, wherein the initial video segment belongs to the second initial video resource.

[0092] Optionally, such as Figure 10 As shown, the first acquisition module 701 further includes: The creation submodule 7015 is used to create the first initial video resource.

[0093] Optionally, such as Figure 11 As shown, the device 700 also includes: The second acquisition module 705 is used to acquire the target game fragment; The recording and accumulation module 706 is used to record modification points and accumulate data for system modeling when a target game segment is deleted; The temporary storage module 707 is used to temporarily store the target game fragment in the user selection area when the target game fragment has not been deleted. Add module 708 to increase the user's video score when the target game segment in the user's selected area is selected by another user and the video image is generated. The synchronization module 709 is used to synchronize the target game segment to other system terminals when the score exceeds the first preset threshold. The cleaning module 710 is used to clean up target game segments when the score is lower than the second preset threshold.

[0094] Optionally, such as Figure 12 As shown, the device 700 also includes: Modification module 711 is used to modify the target game segment based on the target parameters input by the user.

[0095] Optionally, user action parameters include action parameters, gesture parameters, and virtual weapon operation parameters.

[0096] Based on the above Figure 2 In addition to the video image generation method described in the corresponding embodiments, this disclosure also provides a computer-readable storage medium. For example, a non-transitory computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, magnetic tape, a floppy disk, or an optical data storage device. This storage medium stores computer instructions for executing the above-described... Figure 2 The video image generation method described in the corresponding embodiments will not be repeated here.

[0097] Based on the above Figure 2 In addition to the video image generation method described in the corresponding embodiments, this disclosure also provides a chip system including at least one processor. When program instructions are executed in the at least one processor, the at least one processor performs the above-described video image generation method. Figure 2 The video image generation method described in the corresponding embodiments will not be repeated here.

[0098] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0099] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A video image generation method, characterized in that, The method includes: Obtain the initial video clip; The target person in the initial video clip is modeled using the person parameters input by the user; Receive user motion parameters input via motion capture device; Based on the user's action parameters, the modeled target character is subjected to action control to generate the target game segment.

2. The method according to claim 1, characterized in that, After obtaining the initial video segment, the method further includes: Based on the user-set environmental parameters, the target environment in the initial video clip is modeled; the target environment includes, but is not limited to, weather, lighting, background style, and background music.

3. The method according to claim 1, characterized in that, The step of modeling the target person in the initial video clip using user-inputted person parameters includes: When the number of users is not entered, replace the user's selected role information in the initial video clip; or If the number of users entered is less than or equal to the number of characters in the initial video clip, replace the character selected by the user in the initial video clip; or If the number of users entered is greater than the number of characters in the initial video clip, replace all characters in the initial video clip; The target person in the initial video clip is modeled using the person parameters.

4. The method according to claim 1, characterized in that, The process of obtaining the initial video segment includes: Deploy a first initial video resource, the first initial video resource comprising at least one video segment; Play and train to extract target elements from the first initial video resource; If the target elements are extracted correctly, the first initial video resources are sorted according to a preset classification to obtain the second initial video resources; The initial video segment is obtained by selecting from the second initial video resource, and the initial video segment belongs to the second initial video resource.

5. The method according to claim 4, characterized in that, Prior to deploying the first initial video resource, the method further includes: Create the first initial video resource.

6. The method according to claim 1, characterized in that, After generating the target game fragment, the method further includes: Obtain the target game segment; When the target game segment is deleted, the modification point is recorded and data for system modeling is accumulated. If the target game segment is not deleted, the target game segment will be temporarily stored in the user selection area; When the target game segment in the user selection area is selected by another user and a video image is generated, the user's video score is increased; When the score exceeds a first preset threshold, the target game segment will be synchronized to other system terminals; When the score falls below a second preset threshold, the target game segment is cleared.

7. The method according to claim 1, characterized in that, After generating the target game fragment, the method further includes: Based on the target parameters input by the user, the target game segment is modified.

8. A video image generation device, characterized in that, Including memory and processor; The memory is used to store programs; When the program is executed in the processor, the processor is used to perform the method of any one of claims 1-7.

9. A video image generation apparatus, characterized in that, include: The first acquisition module is used to acquire the initial video clip; The modeling module is used to model the target person in the initial video clip based on the person parameters input by the user; The receiving module is used to receive user motion parameters input through the motion capture device; The generation module is used to perform motion control on the modeled target character based on the user's motion parameters in order to generate a target game segment.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium has program instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1-7.

Images