Motion Generation

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts.

Inspired by the strong ties between vision and language, the two intimate human sensing and communication modalities, our paper aims to explore the generation of 3D human full-body motions from texts, as well as its reciprocal task, shorthanded for …

Action2video: Generating Videos of Human 3D Actions

A temporal VAE archtecture model equipped with Lie Algebra representation for action-conditioned 3D human motion generation.

Action2Motion: Conditioned Generation of 3D Human Motions

A temporal VAE archtecture model equipped with Lie Algebra representation for action-conditioned 3D human motion generation.