Use preview method and device for assets

Abstract

The invention relates to a use preview method and device for assets. The selected target assets in the assets can be displayed in response to the selection operation for the assets; and displaying the use effect preview of using the target assets in each target scene, so that a user can intuitively and quickly determine the use effects of the assets in different scenes, further judge the adaptation degrees of different assets, and further quickly search and position the required available assets, thereby saving the time for searching the assets, and improving the efficiency of searching the assets. The asset use efficiency and speed are improved, a large amount of manpower and material resource cost is saved for asset-based content creation, use preview of different assets in different scenes can be carried out by using the effect preview, the effect generated when the target asset is used in the target scene does not depend on subjective imagination of a user any more, and the use experience of the user is improved. The dependence on subjective imagination of the user in content creation is reduced, the trial and error cost is reduced, and the art making process is more efficient.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a method and device for previewing the use of assets. Background Art

[0002] In digital creation, assets usually refer to digital resources such as 3D models, textures, animations, and scenes used in digital content creation, game development, film production, virtual reality, and other fields. These assets can be static, such as a 3D model or texture map, or dynamic, such as an animated character or an interactive scene. For assets in a 3D digital asset library, there are generally several preview methods, such as viewing rendered images, rendered videos, and 3D panoramic images of the assets. However, these methods have limitations and cannot meet the user's preview needs for asset usage. Summary of the invention

[0003] In view of this, the present disclosure proposes a usage preview method and device for assets.

[0004] According to one aspect of the present disclosure, a usage preview method for an asset is provided, the method comprising:

[0005] In response to a selection operation on an asset, displaying a target asset selected from the assets;

[0006] Display a preview of the effect of using the target asset in each target scenario;

[0007] The usage effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene.

[0008] In a possible implementation, the method further includes:

[0009] The rendering of the target asset and the scene information of each target scene are input into a generation model to obtain a preview image of the use effect of using the target asset in each target scene output by the generation model.

[0010] In a possible implementation manner, the scenario information includes description information of the target scenario using the target asset, and the method further includes:

[0011] In response to an information input operation for the target asset, description information of each of the target scenarios for using the target asset determined based on the information input operation is displayed.

[0012] In a possible implementation, the scene information further includes setting information of the target asset in the target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity.

[0013] In a possible implementation, the method further includes:

[0014] Based on the description information of the target scene, at least one auxiliary asset to be used in each of the target scenes is determined, and the use effect preview image includes a rendering of the auxiliary asset.

[0015] In a possible implementation manner, the scene information includes a scene image of the target scene, and the method further includes:

[0016] In response to a selection operation on an optional scene, displaying a scene image of a target scene selected from the optional scenes; or

[0017] A scene image of a target scene imported by a user determined based on the detected scene import operation is displayed.

[0018] In a possible implementation, the scene information further includes setting information of the target asset in each target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity;

[0019] Wherein, the method further comprises:

[0020] In response to input of setting information for the scene image of the target scene, at least one of a setting position, a setting size and a setting quantity of each of the target assets in the scene image is displayed.

[0021] In a possible implementation, the scene information further includes perspective information indicating at least one scene perspective of each of the target scenes, and each usage effect preview image has a corresponding scene perspective.

[0022] In a possible implementation, the rendering of the target asset is a two-dimensional rendering, and the usage effect preview is a two-dimensional image.

[0023] According to another aspect of the present disclosure, a usage preview device for an asset is provided, the device comprising:

[0024] An asset display module, configured to display a selected target asset among the assets in response to a selection operation on the assets;

[0025] A usage effect display module is used to display a preview of the usage effect of the target asset in each target scene;

[0026] The usage effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene.

[0027] In a possible implementation manner, the device further includes:

[0028] The preview image generation module is used to input the rendering image of the target asset and the scene information of each target scene into the generation model to obtain the preview image of the use effect of using the target asset in each target scene output by the generation model.

[0029] In a possible implementation manner, the scenario information includes description information of the target scenario for using the target asset, and the device further includes:

[0030] The description information determination module is used to respond to the information input operation for the target asset and display the description information of each target scenario for using the target asset determined based on the information input operation.

[0031] In a possible implementation, the scene information further includes setting information of the target asset in the target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity.

[0032] In a possible implementation manner, the device further includes:

[0033] The auxiliary asset determination module is used to determine at least one auxiliary asset to be used in each target scene based on the description information of the target scene, and the use effect preview image includes a rendering of the auxiliary asset.

[0034] In a possible implementation manner, the scene information includes a scene image of the target scene, and the device further includes:

[0035] a scene image selection module, configured to display a scene image of a target scene selected from the optional scenes in response to a selection operation on the optional scenes; or

[0036] The scene image import module is used to display the scene image of the target scene imported by the user determined based on the detected scene import operation.

[0037] In a possible implementation, the scene information further includes setting information of the target asset in each target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity;

[0038] Wherein, the device further comprises:

[0039] The setting information display module is used to display at least one of the setting position, setting size and setting quantity of each target asset in the scene image in response to the setting information input for the scene image of the target scene.

[0040] In a possible implementation, the scene information further includes perspective information indicating at least one scene perspective of each of the target scenes, and each usage effect preview image has a corresponding scene perspective.

[0041] In a possible implementation, the rendering of the target asset is a two-dimensional rendering, and the usage effect preview is a two-dimensional image.

[0042] According to another aspect of the present disclosure, a usage preview device for an asset is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0043] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0044] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0045] The use preview method and device for assets provided by the disclosed embodiment can respond to the selection operation for assets and display the selected target assets in the assets; and further display the preview image of the use effect of the target assets in each target scene, so that the user can intuitively and quickly determine the use effect of the assets in different scenes, and then judge the adaptability of different assets, and then quickly find and locate the required available assets, saving the time of finding assets, improving the efficiency and speed of asset use, saving a lot of manpower and material costs for asset-based content creation, and because the use of different assets in different scenes can be previewed through the use effect preview image, the effect of the target asset in the target scene no longer depends on the user's subjective imagination, reducing the dependence on the user's subjective imagination in content creation, reducing the trial and error cost, and making the art production process more efficient.

[0046] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0048] Figure 1 A schematic diagram of an application of a usage preview method for assets according to an embodiment of the present disclosure is shown.

[0049] Figure 2-Figure 4 A schematic diagram showing a method for previewing the use of an asset according to an embodiment of the present disclosure for generating a preview image of the use effect

[0050] Figure 5 It is a block diagram of a device 1900 for previewing usage of an asset according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0052] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0053] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0054] In the process of creating videos, animations, etc., three-dimensional digital assets are the resources needed for creation. In the relevant technology, the assets that have been created can be previewed by viewing the rendered images, rendered videos, three-dimensional panoramic images, etc. of the assets. In some cases, the preview information such as the three-dimensional structure, grid wiring, material mapping, etc. of the assets can be displayed to the user, which can enable the technicians to understand the overall appearance and local details of the assets based on the preview. However, the ultimate purpose of the assets is to be applied to the appropriate scenes. These assets are generally not used independently, but are used in conjunction with other assets in the three-dimensional scene. Under such usage requirements, when the user receives the project requirements and creates for the project, the user needs to imagine the use effect of independent assets in the scene, or the use effect of many independent assets arranged and mixed according to certain rules, which greatly increases the user's judgment cost and also has relatively high requirements for art production experience. Obviously, how to combine the preview of assets with the use of assets in the scene is a technical problem that needs to be solved urgently.

[0055] In order to solve the above technical problems, the disclosed embodiment provides a method and device for previewing the use of assets. It can respond to the selection operation for assets and display the selected target assets in the assets; and further display the preview image of the use effect of the target assets in each target scene, so that the user can intuitively and quickly determine the use effect of the assets in different scenes, and then judge the adaptability of different assets, and then quickly find and locate the required available assets, saving the time of finding assets, improving the efficiency and speed of asset use, and saving a lot of manpower and material costs for asset-based content creation. Moreover, since the use of different assets in different scenes can be previewed through the use effect preview image, the effect of the target asset in the target scene no longer depends on the user's subjective imagination, reducing the dependence on the user's subjective imagination in content creation, reducing the trial and error cost, and making the art production process more efficient.

[0056] The asset usage preview method provided in the embodiment of the present disclosure can be applied to a terminal device or a server. Figure 1 As shown, the method may include: in response to a selection operation on an asset, displaying a target asset selected from the assets, and displaying a preview image of the effect of using the target asset in each target scene.

[0057] The use effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene. The scene information may be information indicating the target scene for using the target asset, the use of the target asset in the target scene, etc., so as to determine how to apply the target asset to the target scene desired by the user.

[0058] In this embodiment, the target assets selected by the user may be one or more, the target scenarios for using each target asset may be one or more, and the final generated usage effect preview images may also be one or more. The user can set them according to actual preview requirements.

[0059] In this embodiment, when the user determines that the target asset meets his / her usage needs based on the usage effect preview image, the user can further download the target asset and store it locally for use in subsequent content creation.

[0060] In this embodiment, the assets for user selection may be assets stored in a pre-set three-dimensional digital asset library. The method may further include: in response to the user's operation, displaying the assets in the three-dimensional digital asset library to the user. Among them, the assets can be displayed to the user by displaying two-dimensional or three-dimensional renderings, thumbnails, names, uses, ages, countries, types and other images and / or text information of each asset from different perspectives. The way to display the assets may be to display them by classification according to the type of assets in the same interface, or to display each asset sequentially in the interface, etc. Then, the user's operation is further detected, and the target asset selected by the user is determined based on the detected selection operation for the asset. Then, the target asset can be highlighted in the displayed assets, or the target asset can be displayed separately in the interface in the manner of displaying the assets described above, and so on. In this way, the user can understand the details of the asset in more detail, have a more accurate understanding of the asset, and have a relatively accurate positioning of the scenario in which it may be applied.

[0061] In some embodiments, the method may further include: in response to an asset search keyword input by a user, displaying multiple assets matching the asset search keyword in the three-dimensional digital asset library to the user. In this way, the user can input the asset search keyword as needed, and then directly search for assets in the three-dimensional digital asset library, and display assets matching the asset search keyword to the user, so that the user can select the desired target asset.

[0062] In the related art, after receiving the project requirements, the user will download the assets that may be applicable to the project in the asset library determined by imagination, and import them into the local project for further use effect testing. This includes asset downloading and importing, asset format conversion, asset arrangement and other tasks. For assets of hundreds of megabytes or thousands of megabytes, the time cost is higher. After receiving the project requirements, the user needs to spend a lot of time to find available assets in the existing asset library and import them into the local project for use effect testing. In the entire art production process, it is a time-consuming link. The method provided by the embodiment of the present disclosure can be combined with a three-dimensional digital asset library. In this way, when the user browses the three-dimensional digital asset library and selects the assets required for the project, the user can directly use the use effect preview image corresponding to the target asset to determine whether the target asset meets the use requirements of the project, and no longer rely solely on imagination to judge whether the asset is available, so that the user can directly download the assets that meet the use requirements and use them, saving the user time to find assets that meet the use needs.

[0063] In a possible implementation, after determining that the user has selected the target asset, a usage setting prompt may be displayed to the user, and the usage setting prompt may be used to remind the user to set a target scene for using the target asset. The user may set the target scene by inputting scene information of the target scene.

[0064] In this implementation, at least one of an input box, a scene image import control, and a scene selection control may be displayed in the usage setting prompt. The input box may allow the user to input description information for the target asset. The scene image import control may allow the user to import scene images for part or all of the target scenes in the target asset. The scene selection control may be used to remind the user to select a target scene from the optional scenes.

[0065] In a possible implementation, the scene information of the target scene may include description information of the target scene using the target asset, and the method may further include: if a trigger operation on the input box is detected, determining that the user needs to input description information, further responding to the information input operation on the target asset, determining the description information input by the user, and displaying the description information of each target scene using the target asset determined based on the information input operation. Figure 2As shown, each usage effect preview image can be generated by the generation model based on the input rendering of the target asset 1 and the description information of each target scene. The user can input the description information in the form of text and / or voice, and the present disclosure does not limit this. In this way, the user can simply input the description information of the scene to obtain the usage efficiency preview image of the target asset applied to the target scene corresponding to the description information. The user operation is simple, and the preview image is generated with high accuracy and fast speed.

[0066] Among them, the description information of the target scene may refer to information that can describe the details of the target scene, which may include environmental information of the target scene (such as geographical location, climate conditions, time, etc.), object information of objects in the target scene (such as objects may be articles, vehicles, buildings, etc., and the object information includes the type, style, age, material, etc. of the objects), organism information of organisms in the target scene (such as organisms may be humans, animals, plants, etc., and the organism information may include the type, action, expression, posture, etc. of the organisms), cultural and social background information (such as the cultural background and social background of the region), economic status information (which may be information reflecting the economic status, such as remote mountainous areas, prosperous cities, etc.), technological development information (which may be information reflecting the level of scientific and technological development, such as the level of electronic products, modes of transportation, etc.), atmosphere information (which may be information expressing the atmosphere in the scene, such as tranquility, romance, noise, warmth, etc.), etc., and the present disclosure does not impose any restrictions on this.

[0067] In a possible implementation, when the scene information includes description information of the target scene, the scene information may also include setting information of the target asset in the target scene, and the setting information includes at least one of a setting position (e.g., a coordinate position in the picture, or a relative position to an object in the target scene, etc.), a setting size, and a setting quantity. In this way, the method of using the target asset in the target scene can be further refined, the difficulty of generating a preview image of the use effect can be simplified, and the generation efficiency and speed can be improved.

[0068] Among them, the setting information can be information indicating how to use the settings of the target asset in the target scene, such as which specific one or several target assets are included in the target scene, the position, size, display angle of the target asset in the target scene, the setting quantity of each target asset, etc., and the present disclosure does not limit this.

[0069] In this implementation, after determining that the user has completed the input of the description information, a setting information input prompt can be displayed to the user to remind the user to input the setting information for the target asset. An input box can be displayed in the setting information input prompt, and the setting information can be determined in response to the information input in the form of text and / or voice after the user triggers the input box, and the present disclosure is not limited to this. In some embodiments, a selection control can also be displayed in the setting information input prompt. In response to the trigger operation for the selection control, the optional options corresponding to the setting position, setting size and setting quantity are displayed to the user, and based on the selection operation for each optional option, the setting position, setting size and setting quantity determined by the user are determined. For example, the optional options for setting the size can include small, normal, and large. The user can determine that the setting size is small through the selection operation, and the target asset in the preview image of the use effect displayed to the user will be displayed in a relatively small size in the target scene. In some embodiments, the setting information can also be included in the description information, that is, the user can also directly enter the setting information while entering the description information.

[0070] In a possible implementation, when the scene information includes description information of the target scene, the scene information may also include renderings of each of the auxiliary assets. The method may also include: based on the description information of the target scene, determining at least one auxiliary asset to be used in each of the target scenes, and the use effect preview image includes a rendering of the auxiliary asset. After determining the description information of the target scene input by the user, the description information can be further analyzed to determine the asset features of the auxiliary assets to be used, and then based on these asset features, the auxiliary assets that can match the asset features can be determined from the three-dimensional digital asset library, and the renderings of these auxiliary assets can be obtained. The auxiliary assets can be the specific objects (such as buildings, people, landscapes, etc.) involved in the description of the target scene in the description information, and the auxiliary assets involved in the description information can be identified based on natural language processing technologies such as keyword matching and part of speech recognition in related technologies. In this way, while the target asset is used in the target scene, auxiliary assets suitable for use with the target asset in the target scene can be displayed to the user, so that subsequent users can use the target assets and auxiliary assets in the target scene as the basis for content creation, simplifying the creation process and providing help for the speed and convenience of content creation.

[0071] In a possible implementation, the scene information may include a scene image of the target scene, and the method may further include: in response to a selection operation for a plurality of optional scenes, displaying a scene image of a target scene selected from the plurality of optional scenes; or, displaying a scene image of a target scene imported by a user determined based on a detected scene import operation. In some embodiments, when the scene image of the target scene is determined, the scene image after content adjustment may be further displayed to the user in response to a content adjustment operation for the scene image. Among them, since the scene image may not fully meet the needs of the user, the user may further adjust the content of the scene image through a content adjustment operation. The content adjustment operation may be an operation to adjust the original content of the scene image, such as color, brightness, and light. The user may change the corresponding content of the scene image by operating the controls such as brightness, color, and light displayed on the scene image. The content adjustment operation may also be to add auxiliary assets to the scene image, and an auxiliary asset selection control may be displayed on the scene image. When a trigger operation for the auxiliary asset selection control is detected, the user is presented with optional alternative auxiliary assets, and then the auxiliary asset selected by the user is determined based on the selection operation for the alternative auxiliary asset, and the rendering of the auxiliary asset is integrated into the scene image for display to the user. Alternatively, when a trigger operation for the auxiliary asset input box displayed on the scene image is detected, the corresponding auxiliary asset is determined based on the auxiliary asset information input by the user, and the rendering of the auxiliary asset is integrated into the scene image for display to the user. In this way, after the scene image of the target scene selected by the user is determined, the scene image can be further adjusted based on the user's content adjustment operation to meet the user's use requirements for the scene image. For example, if the scene image selected by the user is an image of a building during the day, the adjusted scene image may be an image of the building at night; if the scene image selected by the user is a blue sky, the adjusted scene image may be a blue sky containing an airplane.

[0072] In this implementation, in the process of determining that the user has selected the target asset and displaying the usage setting prompt to the user, if a trigger operation for the scene selection control in the usage setting prompt is detected, the scene images of multiple preset optional scenes can be directly displayed to the user, and further based on the detected selection operation, the target scene is determined from the multiple optional scenes, so as to display the scene image of the target scene to the user. Among them, the scene image of the target scene can be highlighted in the scene images of the multiple optional scenes displayed, and the scene image of the target scene can also be displayed above the scene images of the multiple optional scenes displayed. The present disclosure does not impose any restrictions on this. In this way, pre-setting the optional scenes can also simplify the speed at which the user previews the usage effect of the target asset and improve the efficiency of the entire preview process. In this way, the user can select the scene image of the desired target scene as needed, improve the speed and efficiency of the preview process, and more effectively avoid imagination deviations and reduce the cost of frequent trial and error.

[0073] In some embodiments, a scene library may be pre-set, in which scene images of various commonly used scenes are stored, and then in response to a trigger operation on the scene selection control, scene images of multiple optional scenes in the scene library may be displayed to the user. Among them, displaying scene images of multiple optional scenes in the scene library to the user may include: in response to a scene search keyword input by the user, displaying scene images of multiple optional scenes in the scene library that match the scene search keyword to the user. In this way, the user can input the scene search keyword as needed, and then directly search for the optional scenes in the scene library, and display the scene images of the optional scenes that match the scene search keyword to the user, so that the user can select the desired target scene.

[0074] In this implementation, when it is determined that the user has selected the target asset and the usage setting prompt is displayed to the user, if a trigger operation for the scene image import control in the usage setting prompt is detected, the scene image stored locally by the user can be further used as the scene image of the target scene in response to the user's scene import operation, thereby displaying the scene image of the target scene to the user. In this way, the user can set the scene image of the desired target scene according to his or her own personalized needs, improve the speed and efficiency of the preview process, and more effectively avoid imagination deviation and reduce the cost of frequent trial and error.

[0075] In a possible implementation, after determining that the user has imported a scene image of a target scene or that the user has selected a scene image of a target scene from scene images of multiple optional scenes, a setting prompt may be displayed in the process of displaying the scene image of the target scene to the user, and the setting prompt is used to remind the user to set information such as the position, size, and quantity of the target assets used in the scene image of the target scene. Therefore, the method may also include: in response to the input of setting information for the scene image of the target scene, determining at least one of the setting position, setting size, and setting quantity of each target asset in the scene image of the target scene, and then Figure 4 It is shown that the user is displayed at least one of the setting position, setting size and setting quantity of each target asset in the scene image. The implementation method of setting information input may include: the user sets the setting position and setting quantity of the target asset in the scene image by clicking or other operations, and sets the setting size of the corresponding target asset by scaling the schematic object of each setting position. The implementation method of setting information input may also include: text and / or voice input of setting information by triggering the input box in the setting prompt. In this way, the method of using the target asset in the target scene can be further refined, the difficulty of generating the use effect preview image can be simplified, and the generation efficiency and speed can be improved.

[0076] In a possible implementation, when the scene information includes description information or scene images of the target scene, the scene information may also include perspective information indicating at least one scene perspective of each of the target scenes, and each use effect preview image has a corresponding scene perspective. The perspective information may indicate which one or several scene perspectives the use effect preview image to be generated for each target scene needs to have, and the scene perspective may be a front view perspective, a side view perspective, a top view perspective, etc., which is not limited in the present disclosure. In this implementation, after determining that the user has determined the description information or scene image, a perspective setting prompt may be displayed to the user, and the perspective setting prompt may include an input box and / or a perspective selection control for inputting perspective information. The perspective information may be further determined based on the text and / or voice input by the user through the input box; or the user may be further displayed with a trigger operation for the perspective selection control, and then based on the user's selection operation for each alternative scene perspective, the scene perspective selected by the user is determined to form the scene information.

[0077] In this implementation, in the multiple usage effect preview images of the same target asset in the same target scene, different usage effect preview images have corresponding scene perspectives, so that users can understand the usage effects of the target asset at various angles in the target scene based on the usage effect preview images of different scene perspectives, which is convenient for users to make subsequent content. For example, if a target asset is a car, and the target scene is a car driving on a road, the scene perspectives of the corresponding multiple usage effect preview images can be: the front perspective of the vehicle coming towards you, the side perspective of the vehicle passing by, the rear perspective of the vehicle driving away, etc.

[0078] In some embodiments, the target assets in the same usage effect preview image include one or more. Figure 2 The preview of the usage effect is shown Figure 1 , 2 , 3 both include a target asset 1. Figure 4 The preview of the usage effect is shown Figure 5 A target asset 1 is included. Figure 3 The preview of the usage effect is shown Figure 4 The target asset 1 and the target asset 2 are included. For a target asset, a corresponding usage effect preview image can be generated for each target scenario to which it is applied. Figure 2 The preview of the usage effect is shown Figure 1 , 2 , 3 are preview images of the effect of using target asset 1 in three different target scenarios respectively.

[0079] In a possible implementation, the method may further include: inputting a rendering of the target asset and scene information of each of the target scenes into a generation model, and obtaining a preview image of the use effect of using the target asset in each of the target scenes output by the generation model.

[0080] In some embodiments, the rendering of the target asset input into the generated model may be a two-dimensional rendering. When the scene information includes a scene image of the target scene, the scene image may also be a two-dimensional image. The generated preview image of the use effect may be a two-dimensional image. In this way, after viewing the target asset, the user directly generates a two-dimensional preview image of the use effect based on the two-dimensional rendering of the target asset and the scene information. This can reduce the amount of data processing for generating the preview image of the use effect, improve the speed and efficiency of generating the preview image of the use effect, and ensure that the generated preview image of the use effect can meet the user's preview purpose of checking whether the target asset is suitable for use in the target scene. When the target asset is a 3D digital model, the two-dimensional rendering of the target asset may be a rendering of the 3D digital model rendered to a two-dimensional plane based on a pre-set angle. The angle may be set by the user or may be a default angle.

[0081] Among them, the generative model is pre-trained, and the generative model is based on AIGC (Artificial Intelligence Generated Content, artificial intelligence generated content) technology, using at least one of the models such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), Variational Autoencoder (VAE), Generative Adversarial Network (GAN), Diffusion Model (DM), etc., and the construction of the generative model can be set according to actual needs, and the present disclosure does not limit this. For example, the generative model can be a model based on deep learning, including a generative adversarial network and a variational self-encoder. Among them, the generative adversarial network uses a conditional generative adversarial network to input the rendering of the target asset and the scene information of the target scene as conditions, and the generator network generates a realistic preview of the use effect according to these conditions, and the discriminator network is used to distinguish the generated preview image from the real scene image. The variational self-encoder encodes the rendering of the target asset and the scene information of the target scene into a potential representation through the encoder, and then the decoder decodes the potential representation into a preview of the use effect.

[0082] In this embodiment, based on the different scene information, the input information of the generated model includes at least description information of the target scene input or a scene image of the target scene in addition to the rendering of the target asset. Furthermore, in the case where the input information includes the rendering of the target asset and the description information of the target scene, the input information may also include at least one of the setting information of the target asset in the target scene, the perspective information indicating at least one scene perspective of each of the target scenes, and the rendering of the auxiliary asset. In the case where the input information includes the rendering of the target asset and the scene image of the target scene, the input information may also include at least one of the setting information of the target asset in the target scene and the perspective information indicating at least one scene perspective of each of the target scenes.

[0083] In this embodiment, the method may further include a model training step, and the model training step includes:

[0084] The first step is to obtain multiple sample data to form a training data set, each sample data includes: a rendering of at least one asset, scene information corresponding to the scene where the asset is used, and at least one corresponding preview of the use effect. The scene information in each sample data may include a scene image or description information. The scene information in some sample data also includes setting information and / or viewing angle information. The rendering of at least one asset in the sample data and the scene information corresponding to the scene where the asset is used can be used as model input, and the preview of the use effect in the sample data can be used as a label.

[0085] The second step is to train the initial model using the training data set until the model converges to obtain the generated model.

[0086] In a possible implementation, the method may further include: in response to an adjustment operation on the use effect preview image, displaying an adjusted use effect preview image. In the process of displaying the use effect preview image to the user, an adjustment prompt may be displayed to the user to remind the user to adjust the use effect preview image. The adjustment operation may include at least one of the following operations: an operation of adding or modifying the description information, an operation of increasing or decreasing the auxiliary assets, an operation of adjusting the brightness, color, and light of the use effect preview image, an operation of modifying the setting information, an operation of adjusting the scene perspective, an operation of modifying or replacing the scene image of the target scene, etc., and the present disclosure does not limit this. The adjustment operation may be implemented by the user through input text / voice / image, or by the user through the adjustment control displayed in the use effect preview image, and the present disclosure does not limit this. For example, the user may input text and / or voice through the input box in the adjustment prompt to adjust the description information, setting information, auxiliary assets, and scene perspective. The user may change the use effect preview image by operating the adjustment controls such as brightness, color, and light displayed in the use effect preview image.

[0087] The present disclosure also provides a usage preview device for assets, the device comprising:

[0088] An asset display module, configured to display a selected target asset among the assets in response to a selection operation on the assets;

[0089] A usage effect display module is used to display a preview of the usage effect of the target asset in each target scene;

[0090] The usage effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene.

[0091] In a possible implementation manner, the device further includes:

[0092] The preview image generation module is used to input the rendering image of the target asset and the scene information of each target scene into the generation model to obtain the preview image of the use effect of using the target asset in each target scene output by the generation model.

[0093] In a possible implementation manner, the scenario information includes description information of the target scenario for using the target asset, and the device further includes:

[0094] The description information determination module is used to respond to the information input operation for the target asset and display the description information of each target scenario for using the target asset determined based on the information input operation.

[0095] In a possible implementation, the scene information further includes setting information of the target asset in the target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity.

[0096] In a possible implementation manner, the device further includes:

[0097] The auxiliary asset determination module is used to determine at least one auxiliary asset to be used in each target scene based on the description information of the target scene, and the use effect preview image includes a rendering of the auxiliary asset.

[0098] In a possible implementation manner, the scene information includes a scene image of the target scene, and the device further includes:

[0099] a scene image selection module, configured to display a scene image of a target scene selected from the optional scenes in response to a selection operation on the optional scenes; or

[0100] The scene image import module is used to display the scene image of the target scene imported by the user determined based on the detected scene import operation.

[0101] In a possible implementation, the scene information further includes setting information of the target asset in each target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity;

[0102] Wherein, the device further comprises:

[0103] The setting information display module is used to display at least one of the setting position, setting size and setting quantity of each target asset in the scene image in response to the setting information input for the scene image of the target scene.

[0104] In a possible implementation, the scene information further includes perspective information indicating at least one scene perspective of each of the target scenes, and each usage effect preview image has a corresponding scene perspective.

[0105] In a possible implementation, the rendering of the target asset is a two-dimensional rendering, and the usage effect preview is a two-dimensional image.

[0106] It should be noted that although the above embodiments are used as examples to introduce the usage preview method and device for assets, those skilled in the art will understand that the present disclosure should not be limited thereto. In fact, users can flexibly set each step and module according to personal preferences and / or actual application scenarios, as long as they comply with the technical solution of the present disclosure.

[0107] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0108] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0109] The disclosed embodiment also proposes a usage preview device for assets, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0110] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0111] Figure 5 1 is a block diagram of a device 1900 for previewing the use of an asset according to an exemplary embodiment. For example, the device 1900 may be provided as a server or a terminal device. Figure 5 The device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions that can be executed by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above-mentioned usage preview method for an asset.

[0112] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output interface 1958 (I / O interface). The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2000. TM , MacOS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0113] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.

[0114] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0115] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0116] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0117] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0118] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0119] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0120] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0121] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0122] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A usage preview method for an asset, characterized in that: The method comprises: In response to a selection operation on an asset, displaying a target asset selected from the assets; Display a preview of the effect of using the target asset in each target scenario; The usage effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene.

2. The method according to claim 1, characterized in that The method further comprises: The rendering of the target asset and the scene information of each target scene are input into a generation model to obtain a preview image of the use effect of using the target asset in each target scene output by the generation model.

3. The method according to claim 1, characterized in that The scenario information includes description information of the target scenario using the target asset, and the method further includes: In response to an information input operation for the target asset, description information of each of the target scenarios for using the target asset determined based on the information input operation is displayed.

4. The method according to claim 3, characterized in that The scene information also includes setting information of the target asset in the target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity.

5. The method according to claim 3, characterized in that: The method further comprises: Based on the description information of the target scene, at least one auxiliary asset to be used in each of the target scenes is determined, and the use effect preview image includes a rendering of the auxiliary asset.

6. The method according to claim 1, characterized in that The scene information includes a scene image of the target scene, and the method further includes: In response to a selection operation on an optional scene, displaying a scene image of a target scene selected from the optional scenes; or A scene image of a target scene imported by a user determined based on the detected scene import operation is displayed.

7. The method according to claim 6, characterized in that The scene information further includes setting information of the target asset in each target scene, and the setting information includes at least one of a setting position, a setting size, and a setting quantity; Wherein, the method further comprises: In response to input of setting information for the scene image of the target scene, at least one of a setting position, a setting size and a setting quantity of each of the target assets in the scene image is displayed.

8. The method according to claim 3 or 6, characterized in that: The scene information also includes perspective information indicating at least one scene perspective of each target scene, and each usage effect preview image has a corresponding scene perspective.

9. The method according to claim 1, characterized in that: The rendering of the target asset is a two-dimensional rendering, and the usage effect preview is a two-dimensional image.

10. A usage preview device for assets, characterized in that: The device comprises: An asset display module, configured to display a selected target asset among the assets in response to a selection operation on the assets; A usage effect display module is used to display a preview of the usage effect of the target asset in each target scene; The usage effect preview image is generated based on the rendering image of the target asset and the scene information of the target scene.

11. A usage preview device for assets, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 9 when executing the instructions stored in the memory.

12. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product comprising computer readable code, or a non-volatile computer readable storage medium carrying computer readable code, characterized in that: When the computer readable code runs in a processor of an electronic device, the processor in the electronic device executes the method according to any one of claims 1 to 9.

Images