Abstract: A method of generating a locomotion set for a character is disclosed. One or more text inputs specifying movement style and base locomotion speed are received. A forward motion clip is generated using a first model. The first model transforms a noisy sequence into a denoised, prompt-following motion with predicted foot contact states. The forward motion clip is extended to one or more additional motion clips via a second model. The second model synchronizes the one or more additional motion clips to cover multiple directions based on the one or more text inputs. The locomotion set is adjusted based on one or more user interactions.

Abstract: A method of generating or modifying poses in an animation of a character are disclosed. Variable numbers and types of supplied inputs are combined into a single input. The variable numbers and types of supplied inputs correspond to one or more effector constraints for one or more joints of the character. The single input is transformed into a pose embedding. The pose embedding includes a machine-learned representation of the single input. The pose embedding is expanded into a pose representation output. The pose representation output includes local rotation data and global position data for the one or more joints of the character.

Abstract: An AI-assisted texture generation system and method that generates a texture for an object such as a 3D mesh. At a given iteration, the system renders, from a viewpoint, one or more of an object depth and a cumulative texture associated with a cumulative pixel quality map; determines an estimated pixel quality map associated with the viewpoint; generates, at the viewpoint, a new texture associated with the object based on one or more of the object depth, the cumulative texture, and a refine mask; updates the cumulative texture based on the new texture; and updates the cumulative pixel quality map based on the estimated pixel quality map. In some examples, the refine mask is computed based on the cumulative pixel quality map and an estimated pixel quality map. In some examples, the new texture is generating using an augmented inpainting diffusion model for image generation.

Abstract: A method of generating or modifying poses in an animation of a character are disclosed. Variable numbers and types of supplied inputs are combined into a single input. The variable numbers and types of supplied inputs correspond to one or more effector constraints for one or more joints of the character. The single input is transformed into a pose embedding. The pose embedding includes a machine-learned representation of the single input. The pose embedding is expanded into a pose representation output. The pose representation output includes local rotation data and global position data for the one or more joints of the character.

Abstract: A method of estimating a pose for a custom character is disclosed. A skeleton corresponding to a user-supplied character is received or access. Features of the skeleton of the user-supplied character are computed. A set of betas and a scale value that correspond to a skinned multi-person linear (SMPL) model of the user-supplied skeleton are computed. The pose of the skeleton of the custom character is estimated using the SMPL model.

Abstract: A method of optimizing a pose of a character is disclosed. An input is received. The input defines one or more effectors. A pose is generated for the character using a learned inverse kinematics (LIK) machine-learning (ML) component. The LIK ML component is trained using a motion dataset. The generating of the pose is based on one or more criteria. The one or more criteria include explicit intent expressed as the one or more effectors. The generated pose is adjusted using an ordinary inverse kinematics (OIK) component. The OIK component solves an output from the LIK ML component to increase an accuracy at which the explicit intent is reached. A final pose is generated from the adjusted pose. The generating of the final pose includes applying a physics engine (PE) to an output from the OIK component to increase a physics accuracy of the pose.

Abstract: A method of generating or modifying poses in an animation of a character are disclosed. Variable numbers and types of supplied inputs are combined into a single input. The variable numbers and types of supplied inputs correspond to one or more effector constraints for one or more joints of the character. The single input is transformed into a pose embedding. The pose embedding includes a machine-learned representation of the single input. The pose embedding is expanded into a pose representation output. The pose representation output includes local rotation data and global position data for the one or more joints of the character.

Abstract: A method of generating or modifying poses in an animation of a character are disclosed. Variable numbers and types of supplied inputs are combined into a single input. The variable numbers and types of supplied inputs correspond to one or more effector constraints for one or more joints of the character. The single input is transformed into a pose embedding. The pose embedding includes a machine-learned representation of the single input. The pose embedding is expanded into a pose representation output. The pose representation output includes local rotation data and global position data for the one or more joints of the character.