DDCNet : Deep Dilated Convolutional Neural Network for Dense Prediction
Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently larger effective receptive field (ERF) and a higher resolution...
| Veröffentlicht in: | Neurocomputing. - 1998. - 523(2023) vom: 28. Feb., Seite 116-129 |
|---|---|
| 1. Verfasser: | |
| Weitere Verfasser: | |
| Format: | Online-Aufsatz |
| Sprache: | English |
| Veröffentlicht: |
2023
|
| Zugriff auf das übergeordnete Werk: | Neurocomputing |
| Schlagworte: | Journal Article Dense prediction compact network dilated convolution gridding artifact network receptive field optical flow estimation |
| Online verfügbar |
Volltext |