Techniques for selection and inclusion of virtual assets in a virtual scene

1 . A method comprising:

receiving a request for one or more virtual assets of a virtual asset data store to be included in a virtual scene, wherein the request comprises first characteristic data including one or more characteristics associated with the requested one or more virtual assets, and wherein at least a portion of the virtual assets of the virtual asset data store is associated with tags obtained from an output of an artificial intelligence (AI) model;

obtaining a set of tags for the requested one or more virtual assets based on the first characteristic data and second characteristic data indicating one or more characteristics associated with at least one additional virtual asset included in the virtual scene, wherein the set of tags comprises articulation data indicating one or more of a stationary state or a dynamic state of at least one component of a real-world object corresponding to the requested one or more virtual assets relative to another component of the real-world object;

determining, based on the tags associated with the virtual assets of the virtual data store, whether the virtual asset data store identifies a virtual asset that satisfies one or more criteria with respect to the obtained set of tags for the requested one or more virtual assets; and

responsive to determining that the virtual asset data store identifies the virtual asset that satisfies the one or more criteria, providing the virtual asset for inclusion in the virtual scene in accordance with the request.

2 . The method of claim 1 , further comprising:

responsive to determining that the virtual asset data store does not identify a virtual asset associated with a set of tags that satisfies the one or more criteria, providing the first characteristic data to an asset generation engine to generate the virtual asset;

obtaining the generated virtual asset from the asset generation engine; and

providing the generated virtual asset for inclusion in the virtual scene in accordance with the request.

3 . The method of claim 2 , wherein the asset generation engine comprises a generative AI model.

4 . The method of claim 3 , wherein one or more outputs of the generative AI model comprise a model file that, when executed, generates a rendering of an animation of the virtual asset according to the one or more of the stationary state or the dynamic state indicated by the articulation data of the obtained set of tags.

5 . The method of claim 1 , wherein obtaining the set of tags for the requested one or more virtual assets comprises:

providing at least one of the first characteristic data or the second characteristic data as input to the AI model, wherein the AI model is trained to predict one or more tags for a virtual asset based on given characteristic data;

obtaining one or more outputs of the AI model; and

extracting at least one tag of the set of tags from the obtained one or more outputs.

6 . The method of claim 5 , further comprising:

providing articulation data associated with the requested one or more assets as an additional input to the AI model with the at least one of the first characteristic data or the second characteristic data.

7 . The method of claim 1 , wherein determining whether the virtual asset data store identifies a virtual asset that satisfies one or more criteria with respect to the obtained set of tags for the requested one or more virtual assets comprises:

identifying an entry of the virtual asset data store that corresponds to the virtual asset, wherein the identified entry comprises a set of tags associated with the virtual asset; and

determining whether a degree of similarity between the set of tags associated with the virtual asset and the obtained set of tags for the requested one or more virtual assets exceeds a similarity threshold.

8 . The method of claim 1 , wherein the virtual asset provided for inclusion in the virtual scene comprises a three-dimensional (3D) asset.

9 . The method of claim 1 , wherein the request is received via an instance of an application running on a first client device connected to a platform and the virtual asset provided for inclusion in the virtual scene was created by a user via another instance of the application running on a second client device connected to the platform.

10 . The method of claim 1 , further comprising:

updating the virtual asset data store to include a mapping between the obtained set of tags and the virtual asset.

11 . A system comprising:

a memory device; and

a processing device coupled to the memory device, the processing device to perform operations comprising:

receiving a request for one or more virtual assets of a virtual asset data store to be included in a virtual scene, wherein the request comprises first characteristic data including one or more characteristics associated with the requested one or more virtual assets, and wherein at least a portion of the virtual assets of the virtual asset data store is associated with tags obtained from an output of an artificial intelligence (AI) model;

obtaining a set of tags for the requested one or more virtual assets based on the first characteristic data and second characteristic data indicating one or more characteristics associated with at least one additional virtual asset included in the virtual scene, wherein the set of tags comprises articulation data indicating one or more of a stationary state or a dynamic state of at least one component of a real-world object corresponding to the requested one or more virtual assets relative to another component of the real-world object;

determining, based on the tags associated with the virtual assets of the virtual data store, whether the virtual asset data store identifies a virtual asset that satisfies one or more criteria with respect to the obtained set of tags for the requested one or more virtual assets; and

responsive to determining that the virtual asset data store identifies the virtual asset that satisfies the one or more criteria, providing the virtual asset for inclusion in the virtual scene in accordance with the request.

12 . The system of claim 11 , wherein the operations further comprise:

responsive to determining that the virtual asset data store does not identify a virtual asset associated with a set of tags that satisfies the one or more criteria, providing the first characteristic data to an asset generation engine to generate the virtual asset;

obtaining the generated virtual asset from the asset generation engine; and

providing the generated virtual asset for inclusion in the virtual scene in accordance with the request.

13 . The system of claim 12 , wherein the asset generation engine comprises a generative AI model.

14 . The system of claim 13 , wherein one or more outputs of the generative AI model comprise a model file that, when executed, generates a rendering of an animation of the virtual asset according to the one or more of the stationary state or the dynamic state indicated by the articulation data of the obtained set of tags.

15 . The system of claim 11 , wherein obtaining the set of tags for the requested one or more virtual assets comprises:

providing at least one of the first characteristic data or the second characteristic data as input to the AI model, wherein the AI model is trained to predict one or more tags for a virtual asset based on given characteristic data;

obtaining one or more outputs of the AI model; and

extracting at least one tag of the set of tags from the obtained one or more outputs.

16 . The system of claim 15 , wherein the operations further comprise:

providing articulation data associated with the requested one or more assets as an additional input to the AI model with the at least one of the first characteristic data or the second characteristic data.

17 . The system of claim 11 , wherein determining whether the virtual asset data store identifies a virtual asset that satisfies one or more criteria with respect to the obtained set of tags for the requested one or more virtual assets comprises:

identifying an entry of the virtual asset data store that corresponds to the virtual asset, wherein the identified entry comprises a set of tags associated with the virtual asset; and

determining whether a degree of similarity between the set of tags associated with the virtual asset and the obtained set of tags for the requested one or more virtual assets exceeds a similarity threshold.

18 . The system of claim 11 , wherein the virtual asset provided for inclusion in the virtual scene comprises a three-dimensional (3D) asset.

19 . The system of claim 11 , wherein the operations further comprise:

updating the virtual asset data store to include a mapping between the obtained set of tags and the virtual asset.

20 . A non-transitory computer readable storage medium comprising instructions for a server that, when executed by a processing device, cause the processing device to perform operations comprising:

receiving a request for one or more virtual assets of a virtual asset data store to be included in a virtual scene, wherein the request comprises first characteristic data including one or more characteristics associated with the requested one or more virtual assets, and wherein at least a portion of the virtual assets of the virtual asset data store is associated with tags obtained from an output of an artificial intelligence (AI) model;

obtaining a set of tags for the requested one or more virtual assets based on the first characteristic data and second characteristic data indicating one or more characteristics associated with at least one additional virtual asset included in the virtual scene, wherein the set of tags comprises articulation data indicating one or more of a stationary state or a dynamic state of at least one component of a real-world object corresponding to the requested one or more virtual assets relative to another component of the real-world object;

determining, based on the tags associated with the virtual assets of the virtual data store, whether the virtual asset data store identifies a virtual asset that satisfies one or more criteria with respect to the obtained set of tags for the requested one or more virtual assets; and

responsive to determining that the virtual asset data store identifies the virtual asset that satisfies the one or more criteria, providing the virtual asset for inclusion in the virtual scene in accordance with the request.