Name
Abstract | ||
|---|---|---|
Image understanding under the foggy scene is greatly challenging due to inhomogeneous visibility deterioration. Although various image dehazing methods have been proposed, they usually aim to improve image visibility (such as, PSNR/SSIM) in the pixel space rather than the feature space, which is critical for the perception of computer vision. Due to this mismatch, existing dehazing methods are limited or even adverse in facilitating the foggy scene understanding. In this paper, we propose a generalized deep feature refinement module to minimize the difference between clear images and hazy images in the feature space. It is consistent with the computer perception and can be embedded into existing detection or segmentation backbones for joint optimization. Our feature refinement module is built upon the graph convolutional network, which is favorable in capturing the contextual information and beneficial for distinguishing different semantic objects. We validate our method on the detection and segmentation tasks under foggy scenes. Extensive experimental results show that our method outperforms the state-of-the-art dehazing based pretreatments and the fine-tuning results on hazy images. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MMSP48831.2020.9287089 | 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | DocType | ISSN |
Semantic foggy scene understanding,feature refinement,graph convolutional network | Conference | 2163-3517 |
ISBN | Citations | PageRank |
978-1-7281-9323-6 | 0 | 0.34 |
References | Authors | |
4 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hui Li | 1 | 123 | 45.57 |
| Qingbo Wu | 2 | 399 | 39.78 |
| Haoran Wei | 3 | 7 | 6.58 |
| King Ngi Ngan | 4 | 2383 | 185.21 |
| Hongliang Li | 5 | 1833 | 101.92 |
| Fanman Meng | 6 | 549 | 33.61 |
| Linfeng Xu | 7 | 117 | 19.16 |