Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy
For CNNs based stereo matching methods, cost volumes play an important role in achieving good matching accuracy. In this paper, we present an end-to-end trainable convolution neural network to fully use cost volumes for stereo matching. Our network consists of three sub-modules, i.e., shared feature...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 1 vom: 22. Jan., Seite 300-315
|
|---|
| 1. Verfasser: |
Liang, Zhengfa
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Guo, Yulan,
Feng, Yiliu,
Chen, Wei,
Qiao, Linbo,
Zhou, Li,
Zhang, Jianfeng,
Liu, Hengzhu |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|