Generating interactive messages with asynchronous media content

1. A method comprising:

receiving, by a computing device, a first media content item associated with a first interactive object of an interactive message;

receiving, by a computing device, a second media content item associated with a second interactive object of the interactive message;

generating, by the computing device, a third media content item based on the first media content item and second media content item, wherein the third media content item comprises combined features of the first media content item and the second media content item; and

causing, by the computing device, display of the generated third media content item.

2. The method of claim 1 , wherein the first media content item comprises an image of a first user and the second media content item comprises an image of a second user.

3. The method of claim 1 , wherein generating the third media content item based on the first media content item and the second media content item comprises:

generating a first feature vector for the first image;

generating a second feature vector for the second image;

combining the first feature vector and the second feature vector to generate a combined feature vector; and

rendering the third image from the combined feature vector.

4. The method of claim 3 , wherein combining the first feature vector and the second feature vector to generate the combined feature vector comprises averaging features represented in the first feature vector and the second feature vector to generate the combined feature vector comprising the averaged features.

5. The method of claim 4 , wherein a first weight is associate with the first feature vector and a second weight is associated with the second feature vector, and wherein the features represented in the first feature vector and the second feature vector are weighted according to the first weight and second weight to generate the averaged features of the combined feature vector.

6. The method of claim 3 , wherein the first feature vector is generating by:

generating a mesh of the first media content item, the mesh comprising a three-dimensional model of the first media content item;

generating a vector representing a feature type for the one or more features indicated in the mesh;

generating a texture of the first media content item, the texture indicating color values in the mesh of the first media content item;

generating a vector representing the texture of the first media content item; and

combining the vector representing a feature type for the one or more features indicated in the mesh and the vector representing the texture of the first media content item to generate the first feature vector.

7. The method of claim 6 , wherein the feature type indicates a shape of the feature.

8. The method of claim 3 , wherein rendering the third image from the combined feature vector comprises applying the combined feature vector to a target template mesh and rendering the target template mesh to generate the third image.

9. The method of claim 1 , wherein the computing device is part of a server system and causing display of the generated third media content item comprises providing the third media content item to a second computing device for display on the second computing device.

10. The method of claim 1 , wherein the computing device is a first computing device and wherein the first media content item is received from a second computing device and the second media content item is received from a camera device of the first computing device.

11. A computing device comprising:

a memory that stores instructions; and

one or more processors configured by the instructions to perform operations comprising:

receiving a first media content item associated with a first interactive object of an interactive message;

receiving a second media content item associated with a second interactive object of the interactive message;

generating a third media content item based on the first media content item and second media content item, wherein the third media content item comprises combined features of the first media content item and the second media content item; and

causing display of the generated third media content item.

12. The computing device of claim 11 , wherein the first media content item comprises an image of a first user and the second media content item comprises an image of a second user.

13. The computing device of claim 11 , wherein generating the third media content item based on the first media content item and the second media content item comprises:

generating a first feature vector for the first image;

generating a second feature vector for the second image;

combining the first feature vector and the second feature vector to generate a combined feature vector; and

rendering the third image from the combined feature vector.

14. The computing device of claim 13 , wherein combining the first feature vector and the second feature vector to generate the combined feature vector comprises averaging features represented in the first feature vector and the second feature vector to generate the combined feature vector comprising the averaged features.

15. The computing device of claim 14 , wherein a first weight is associate with the first feature vector and a second weight is associated with the second feature vector, and wherein the features represented in the first feature vector and the second feature vector are weighted according to the first weight and second weight to generate the averaged features of the combined feature vector.

16. The computing device of claim 13 , wherein the first feature vector is generating by:

generating a mesh of the first media content item, the mesh comprising a three-dimensional model of the first media content item;

generating a vector representing a feature type for the one or more features indicated in the mesh;

generating a texture of the first media content item, the texture indicating color values in the mesh of the first media content item;

generating a vector representing the texture of the first media content item; and

combining the vector representing a feature type for the one or more features indicated in the mesh and the vector representing the texture of the first media content item to generate the first feature vector.

17. The computing device of claim 16 , wherein the feature type indicates a shape of the feature.

18. The computing device of claim 13 , wherein rendering the third image from the combined feature vector comprises applying the combined feature vector to a target template mesh and rendering the target template mesh to generate the third image.

19. The computing device of claim 11 , wherein the computing device is part of a server system and causing display of the generated third media content item comprises providing the third media content item to a second computing device for display on the second computing device.

20. A non-transitory computer-readable medium comprising instructions stored thereon that are executable by at least one processor to cause a computing device to perform operations comprising:

receiving a first media content item associated with a first interactive object of an interactive message;

receiving a second media content item associated with a second interactive object of the interactive message;

generating a third media content item based on the first media content item and second media content item, wherein the third media content item comprises combined features of the first media content item and the second media content item; and

causing display of the generated third media content item.