NVDS + : Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation
Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce consistency from data, which requires well-designed models...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 08. Okt.
|
|---|
| 1. Verfasser: |
Wang, Yiran
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Shi, Min,
Li, Jiaqi,
Hong, Chaoyi,
Huang, Zihao,
Peng, Juewen,
Cao, Zhiguo,
Zhang, Jianming,
Xian, Ke,
Lin, Guosheng |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2024
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|