Electronic Arts Inc.

Elaheh Akhoundi

Fabio Zinno

This specification relates to the generation of animation data using recurrent neural networks. According to a first aspect of this specification, there is described a computer implemented method comprising: sampling an initial hidden state of a recurrent neural network (RNN) from a distribution; generating, using the RNN, a sequence of frames of animation from the initial state of the RNN and an initial set of animation data comprising a known initial frame of animation, the generating comprising, for each generated frame of animation in the sequence of frames of animation: inputting, into the RNN, a respective set of animation data comprising the previous frame of animation data in the sequence of frames of animation; generating, using the RNN and based on a current hidden state of the RNN, the frame of animation data; and updating the hidden state of the RNN based on the input respective set of animation data.

Animation generation and interpolation with RNN-based variational autoencoders

Systems and methods are provided for enhanced pose generation based on generative modeling. An example method includes accessing an autoencoder trained based on poses of real-world persons, each pose being defined based on location information associated with joints, with the autoencoder being trained to map an input pose to a feature encoding associated with a latent feature space. Information identifying, at least, a first pose and a second pose associated with a character configured for inclusion in an in-game world is obtained via user input, with each of the poses being defined based on location information associated with the joints and with the joints being included on a skeleton associated with the character. Feature encodings associated with the first pose and the second pose are generated based on the autoencoder. Output poses are generated based on transition information associated with the first pose and the second pose.

Enhanced pose generation based on generative modeling

Systems and methods are provided for enhanced pose generation based on conditional modeling of inverse kinematics. An example method includes accessing an autoencoder trained based on poses, with each pose being defined based on location information of joints, and the autoencoder being trained based on conditional information indicating positions of a subset of the joints. The autoencoder is trained to reconstruct, via a latent variable space, each pose based on the conditional information. Information specifying positions of the subset of the joints is obtained via an interactive user interface and the latent variable space is sampled. An output is generated for inclusion in the interactive user interface based on the sampling and the positions.

Enhanced pose generation based on conditional modeling of inverse kinematics

According to a first aspect of this specification, there is described a computer-implemented method of tagging video frames. The method comprises generating, using a frame tagging model, a tag for each of a plurality of frames of an animation sequence. The frame tagging model comprises: a first neural network portion configured to process, for each frame of the plurality of frames, a plurality of features associated with the frame and generate an encoded representation for the frame. The frame tagging model further comprises a second neural network portion configured to receive input comprising the encoded representations of each frame and generate output indicative of a tag for each of the plurality of frames.

Machine-learning models for tagging video frames

Systems and methods are provided for enhanced animation generation based on conditional modeling. An example method includes accessing an autoencoder trained based on poses and conditional information associated with the poses, each pose being defined based on location information associated with joints, and the conditional information for each pose reflecting prior poses of the pose, with the autoencoder being trained to reconstruct, via a latent variable space, each pose based on the conditional information. Poses in a sequence of poses, are obtained via an interactive user interface, and the latent variable space is sampled. An output pose is generated based on the sampling, the output pose being included in the interactive user interface.

Growing community of inventors

Vancouver, Canada

Elaheh Akhoundi