Recurrent Multiscale Feature Modulation for Geometry Consistent Depth Learning
The U-Net-like coarse-to-fine network design is currently the dominant choice for dense prediction tasks. Although this design can often achieve competitive performance, it suffers from some inherent limitations, such as training error propagation from low to high resolution and the dependency on th...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 12 vom: 28. Nov., Seite 9551-9566
|
|---|
| 1. Verfasser: |
Zhou, Zhongkai
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Fan, Xinnan,
Shi, Pengfei,
Xin, Yuanxue,
Duan, Dongliang,
Yang, Liuqing |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2024
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|