Abstract: Video-based 3D human pose estimation has achieved great progress, however, it is still difficult to learn precise 2D-3D projection under some hard cases. Multi-level human knowledge and ...
Abstract: Human pose transfer has typically been modeled as a 2D image-to-image translation problem. This formulation ignores the human body shape prior in 3D space and inevitably causes implausible ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results