PARE: Part Attention Regressor for 3D Human Body Estimation
2021-10-12
PARE regresses 3D human pose and shape using part-guided attention. It learns to be robust to occlusion, making it much more practical than recent methods when applied to real images.
| Author(s): | Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, and Michael J. Black |
| Department(s): |
Perceiving Systems |
| Research Projects(s): |
Regressing Humans |
| Publication(s): |
{PARE}: Part Attention Regressor for {3D} Human Body Estimation
|
| Authors: | Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, and Michael J. Black |
| Release Date: | 2021-10-12 |
| Repository: | https://github.com/mkocabas/PARE |
| External Link: | https://pare.is.tue.mpg.de/ |
