Electronic Arts Inc.

Electronics Arts, Inc.

Fabio Zinno

Elaheh Akhoundi

Tom Waterson

Ben Folsom Carter, Jr

Michiel Van De Panne

George Cheng

Jalpesh Sachania

Hung Yu Ling

Some embodiments herein can include methods and systems for predicting next poses of a character within a virtual gaming environment. The pose prediction system can identify a current pose of a character, generate a gaussian distribution representing a sample of likely poses based on the current pose, and apply the gaussian distribution to the decoder. The decoder can be trained to generate a predicted pose based on a gaussian distribution of likely poses. The system can then render the predicted next pose of the character within the three-dimensional virtual gaming environment. Advantageously, the pose prediction system can apply a decoder that does not include or use input motion capture data that was used to train the decoder.

Character controllers using motion variational autoencoders (MVAEs)

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

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.

Enhanced animation generation based on conditional modeling

Methods for improving animation of a character in a simulation by using physics driven by muscle activation data are provided. In one aspect, a method includes detecting a first trigger for a character to perform a movement. Animation data for the character is selected based on the first trigger. A muscle state corresponding to a body part of the character is determined based on the animation data. The movement is performed based on the animation data. A second trigger for altering the movement is detected. The movement is changed based on the muscle state and the second trigger. Systems and machine-readable media are also provided.

Computer architecture for animation of a character in a simulation based on muscle activation data

Embodiments of systems disclosed herein reduce or eliminate artifacts or visible discrepancies that may occur when transitioning from one animation to another animation. In certain embodiments, systems herein identify one or more pose or reference features for one or more objects in a frame of a currently displayed animation. Although not limited as such, often the one or more objects are characters within the animation. Systems herein can attempt to match the reference features for the one or more objects to reference features of corresponding objects in a set of potential starting frames for a second animation that is to start being displayed. The potential starting frame with reference features that are an acceptable match with the current frame of the current animation may be selected as a starting frame for playing the second, animation potentially resulting in a smoother transition than starting from the first frame.

System for seamless animation transition

Embodiments of systems disclosed herein may use example based procedural animation techniques to create smooth, lifelike animations. Systems herein can identify a character pose at the end of each game update frame. Reference features can be extracted from the game update frame and may be used to identify a specific motion capture frame to use in generating an animation. The selected motion capture frame can be used as an initial target frame for a subsequent frame. Further, the target frame may be modified in response to a collision event. Based on the extracted reference feature information and the applied external forces due to the collision event, a new motion capture frame may be selected thereby, creating a new animation that appears more realistic compared to previous systems.

Growing community of inventors

Vancouver, Canada

Fabio Zinno