OIFlow : Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning
Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can provide effective information for optical flow learning. In...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 07., Seite 6420-6433
|
|---|
| 1. Verfasser: |
Liu, Shuaicheng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Luo, Kunming,
Ye, Nianjin,
Wang, Chuan,
Wang, Jue,
Zeng, Bing |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|