DoubleFusion : Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
We propose DoubleFusion, a new real-time system that combines volumetric non-rigid reconstruction with data-driven template fitting to simultaneously reconstruct detailed surface geometry, large non-rigid motion and the optimized human body shape from a single depth camera. One of the key contributi...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 42(2020), 10 vom: 22. Okt., Seite 2523-2539
|
|---|
| 1. Verfasser: |
Yu, Tao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zhao, Jianhui,
Zheng, Zerong,
Guo, Kaiwen,
Dai, Qionghai,
Li, Hao,
Pons-Moll, Gerard,
Liu, Yebin |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2020
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|