Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2310.20210 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913326868463616 |
|---|---|
| author | Chen, Weiwen Lei, Yingtie Luo, Shenghong Zhou, Ziyang Li, Mingxian Pun, Chi-Man |
| author_facet | Chen, Weiwen Lei, Yingtie Luo, Shenghong Zhou, Ziyang Li, Mingxian Pun, Chi-Man |
| contents | Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_20210 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer Chen, Weiwen Lei, Yingtie Luo, Shenghong Zhou, Ziyang Li, Mingxian Pun, Chi-Man Computer Vision and Pattern Recognition Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement techniques, there exist several problems that demand further improvement: (i) The current deep learning methods rely on Convolutional Neural Networks (CNNs) that lack the multi-scale enhancement, and global perception field is also limited. (ii) The scarcity of paired real-world underwater datasets poses a significant challenge, and the utilization of synthetic image pairs could lead to overfitting. To address the aforementioned problems, this paper introduces a Multi-scale Transformer-based Network called UWFormer for enhancing images at multiple frequencies via semi-supervised learning, in which we propose a Nonlinear Frequency-aware Attention mechanism and a Multi-Scale Fusion Feed-forward Network for low-frequency enhancement. Besides, we introduce a special underwater semi-supervised training strategy, where we propose a Subaqueous Perceptual Loss function to generate reliable pseudo labels. Experiments using full-reference and non-reference underwater benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of both quantity and visual quality. |
| title | UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.20210 |