Name
Abstract | ||
|---|---|---|
Image dehazing aims to recover a clean image from a hazy image, which is a challengingly longstanding problem. In this paper, we propose an Ensemble Multi-scale Residual Attention Network (EMRA-Net) to directly generate a clean image, which include two parts: a three-scale residual attention CNN (TRA-CNN), and an ensemble attention CNN (EA-CNN). In TRA-CNN, we employ wavelet transform to obtain the downsampled images, instead of using common spatial downsampling methods, such as nearest downsampling and strided-convolution. With the help of wavelet transform, we can avoid the loss of image texture details. Moreover, in each scale-branch, Res2Net modules are connected in series to make full use of the hierarchical features from the original hazy images, and channel attention mechanism is introduced to focus channel-dimension information. Finally, an EA-CNN is proposed to fuse coarse images generated from TRA-CNN into a refined clean image. Extensive experiments on the benchmark synthetic hazy datasets and the real-world hazy dataset prove that proposed EMRA-Net is superior to previous state-of-the-art methods both in subjective visual perception and objective image quality assessment metrics. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1007/s11042-021-11081-x | MULTIMEDIA TOOLS AND APPLICATIONS |
Keywords | DocType | Volume |
Image dehazing, Convolutional neural network, Residual learning, Channel attention | Journal | 80 |
Issue | ISSN | Citations |
19 | 1380-7501 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jixiao Wang | 1 | 0 | 0.34 |
| Chao-feng Li | 2 | 148 | 16.45 |
| Shoukun Xu | 3 | 1 | 1.71 |