A Sampling Approach to Generating Closely Interacting 3D Pose-Pairs from 2D Annotations
We introduce a data-driven method to generate a large number of plausible, closely interacting 3D human pose-pairs, for a given motion category, e.g., wrestling or salsa dance. With much difficulty in acquiring close interactions using 3D sensors, our approach utilizes abundant existing video data w...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on visualization and computer graphics. - 1996. - 25(2019), 6 vom: 30. Juni, Seite 2217-2227
|
|---|
| 1. Verfasser: |
Yin, Kangxue
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Huang, Hui,
Ho, Edmond S L,
Wang, Hao,
Komura, Taku,
Cohen-Or, Daniel,
Zhang, Hao |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2019
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on visualization and computer graphics
|
|---|
| Schlagworte: | Journal Article |
|---|