Robust 3D Human Pose Estimation from Single Images or Video Sequences
We propose a method for estimating 3D human poses from single images or video sequences. The task is challenging because: (a) many 3D poses can have similar 2D pose projections which makes the lifting ambiguous, and (b) current 2D joint detectors are not accurate which can cause big errors in 3D est...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 41(2019), 5 vom: 08. Mai, Seite 1227-1241
|
|---|
| 1. Verfasser: |
Wang, Chunyu
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Wang, Yizhou,
Lin, Zhouchen,
Yuille, Alan L |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2019
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S. |
|---|