Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916323081060352 |
|---|---|
| author | Fan, Shuaibin Xue, Minglong Ning, Aoxiang Zhong, Senming |
| author_facet | Fan, Shuaibin Xue, Minglong Ning, Aoxiang Zhong, Senming |
| contents | Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing model (DCM-dehaze) to address this issue. The proposed method consists of two collaborative branches: dehazing and contour constraints. Specifically, we design a dual depthwise separable convolutional module (DDSCM) to enhance the information expressiveness of deeper features and the correlation to shallow features. In addition, we construct a bidirectional contour function to optimize the edge features of the image to enhance the clarity and fidelity of the image details. Furthermore, we present feature enhancers via a residual dense architecture to eliminate redundant features of the dehazing process and further alleviate the domain deviation problem. Extensive experiments on benchmark datasets show that our method reaches the state-of-the-art. This project code will be available at \url{https://github.com/Fan-pixel/DCM-dehaze. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10226 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing Fan, Shuaibin Xue, Minglong Ning, Aoxiang Zhong, Senming Computer Vision and Pattern Recognition Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing model (DCM-dehaze) to address this issue. The proposed method consists of two collaborative branches: dehazing and contour constraints. Specifically, we design a dual depthwise separable convolutional module (DDSCM) to enhance the information expressiveness of deeper features and the correlation to shallow features. In addition, we construct a bidirectional contour function to optimize the edge features of the image to enhance the clarity and fidelity of the image details. Furthermore, we present feature enhancers via a residual dense architecture to eliminate redundant features of the dehazing process and further alleviate the domain deviation problem. Extensive experiments on benchmark datasets show that our method reaches the state-of-the-art. This project code will be available at \url{https://github.com/Fan-pixel/DCM-dehaze. |
| title | Addressing Domain Discrepancy: A Dual-branch Collaborative Model to Unsupervised Dehazing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.10226 |