Abstract | ||
---|---|---|
We propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining, and dehazing. These problems usually involve estimating two components of the target signals: structures and details. Motivated by this, we design the proposed DualCNN to have two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate desired signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods that have been specially designed for each individual task. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s11263-022-01583-y | International Journal of Computer Vision |
Keywords | DocType | Volume |
Low-level vision, Image restoration, Image filtering, Image enhancement, Dual convolutional neural network | Journal | 130 |
Issue | ISSN | Citations |
6 | 0920-5691 | 0 |
PageRank | References | Authors |
0.34 | 45 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jin-shan Pan | 1 | 567 | 30.84 |
Deqing Sun | 2 | 1061 | 44.84 |
Jiawei Zhang | 3 | 111 | 11.52 |
Jinhui Tang | 4 | 5180 | 212.18 |
Jian Yang | 5 | 6102 | 339.77 |
Yu-Wing Tai | 6 | 2028 | 92.75 |
Yang Ming-Hsuan | 7 | 15303 | 620.69 |