Multi-Dimensional Residual Dense Attention Network for Stereo Matching
Very deep convolutional neural networks (CNNs) have recently achieved great success in stereo matching. It is still highly desirable to learn a robust feature map to improve ill-posed regions, such as weakly textured regions, reflective surfaces, and repetitive patterns. Therefore, we propose an end...
Bewaard in:
| Hoofdauteurs: | , , , , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
IEEE
2019-01-01
|
| Reeks: | IEEE Access |
| Onderwerpen: | |
| Online toegang: | https://ieeexplore.ieee.org/document/8694010/ |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|