6 datasets found

The dataset proposed by Xia et al. (2015) contains six content classes and eight different styles for each type of motion.

Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be...

Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be...

Single Motion Diffusion Model, a model designed to learn the internal motifs of a single motion sequence with arbitrary topology and synthesize motions of arbitrary length that...

The dataset used in the paper for human motion synthesis and reconstruction.

Motions are from two publicly available datasets: Xia et al. [Xia et al. 2015] and HumanAct12 [Guo et al. 2020].