research
∙
05/16/2022
TOCH: Spatio-Temporal Object Correspondence to Hand for Motion Refinement
We present TOCH, a method for refining incorrect 3D hand-object interact...
share
research
∙
08/18/2021
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
Depth estimation, as a necessary clue to convert 2D images into the 3D s...
research
∙
02/01/2021
Adjoint Rigid Transform Network: Self-supervised Alignment of 3D Shapes
Most learning methods for 3D data (point clouds, meshes) suffer signific...
research
∙
07/22/2020
Unsupervised Shape and Pose Disentanglement for 3D Meshes
Parametric models of humans, faces, hands and animals have been widely u...
research
∙
01/05/2018