Abstract: An animation system wherein a machine learning model is adopted to learn a transformation relationship between facial muscle movements and skin surface movements. For example, for the skin surface representing “smile,” the transformation model derives movement vectors relating to what facial muscles are activated, what are the muscle strains, what is the joint movement, and/or the like. Such derived movement vectors may be used to simulate the skin surface “smile.

Abstract: An animation system wherein scanned facial expressions are processed to form muscle models that can be used to generate expressions based on specification of a strain vector and a control vector of the muscle model.

Abstract: An animation system wherein scanned facial expressions are processed to form muscle models that can be used to generate expressions based on specification of a strain vector and a control vector of the muscle model.

Abstract: An animation system wherein a machine learning model is adopted to generate animated facial actions based on parameters obtained from a live actor. Specifically, the anatomical structure such as a facial muscle topology and a skull surface that are specific to the live actor may be used. A muscle structure of simplified “pseudo” muscles that approximate the actual muscle topology but with reduced degree of freedom is determined to improve computational efficiency.

Abstract: An animation system wherein a machine learning model is adopted to learn a transformation relationship between facial muscle movements and skin surface movements. For example, for the skin surface representing “smile,” the transformation model derives movement vectors relating to what facial muscles are activated, what are the muscle strains, what is the joint movement, and/or the like. Such derived movement vectors may be used to simulate the skin surface “smile.

Abstract: An apparatus for motion transformation according to an embodiment of the present disclosure includes a basic data input unit through which basic motion data is inputted, a pre-processing unit which acquires a parameter through pre-processing of the inputted basic motion data, a motion transformation unit which performs biomechanical observations-based gait motion transformation processing based on the pre-processed parameter and age input information, and an output unit which outputs the transformation processed motion.

Abstract: An animation system wherein a machine learning model is adopted to generate animated facial actions based on parameters obtained from a live actor. Specifically, the anatomical structure such as a facial muscle topology and a skull surface that are specific to the live actor may be used. A skull surface that is specific to a live actor based on facial scans of the live actor and generic tissue depth data. For example, the facial scans of the live actor may provide a skin surface topology of the live actor, based on which the skull surface underneath the skin surface can be derived by “offsetting” the skin surface with corresponding soft tissue depth at different sampled points on the skin surface.

Abstract: The present disclosure relates to a motion retargeting method and apparatus for character animation, and the method may include generating an intermediate object including at least one of a skeleton and a mesh based on a source motion and a target character, extracting keyframes of the intermediate object, constituting target rig parameters based on the extracted keyframes, and performing spacetime optimization on the target rig parameters to minimize a pose error between the intermediate object and the target character.

Abstract: The present disclosure relates to a motion retargeting method and apparatus for character animation, and the method may include generating an intermediate object including at least one of a skeleton and a mesh based on a source motion and a target character, extracting keyframes of the intermediate object, constituting target rig parameters based on the extracted keyframes, and performing spacetime optimization on the target rig parameters to minimize a pose error between the intermediate object and the target character.

Abstract: An apparatus for motion transformation according to an embodiment of the present disclosure includes a basic data input unit through which basic motion data is inputted, a pre-processing unit which acquires a parameter through pre-processing of the inputted basic motion data, a motion transformation unit which performs biomechanical observations-based gait motion transformation processing based on the pre-processed parameter and age input information, and an output unit which outputs the transformation processed motion.

Abstract: Disclosed is a method for providing a rigging tool. The method for providing a rigging tool includes receiving an input character, generating a basic rigging at the input character by using a skeleton extraction technique and a skinning weight technique, and providing a skeleton correction function and a skinning weight correction function on the basis of the generated basic rigging.