Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.01497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918333085908992 |
|---|---|
| author | Zhao, Chen Dong, Chenyu Cai, Weiling Wang, Yueyue |
| author_facet | Zhao, Chen Dong, Chenyu Cai, Weiling Wang, Yueyue |
| contents | Underwater visuals undergo various complex degradations, inevitably influencing the efficiency of underwater vision tasks. Recently, diffusion models were employed to underwater image enhancement (UIE) tasks, and gained SOTA performance. However, these methods fail to consider the physical properties and underwater imaging mechanisms in the diffusion process, limiting information completion capacity of diffusion models. In this paper, we introduce a novel UIE framework, named PA-Diff, designed to exploiting the knowledge of physics to guide the diffusion process.
PA-Diff consists of Physics Prior Generation (PPG) Branch, Implicit Neural Reconstruction (INR) Branch, and Physics-aware Diffusion Transformer (PDT) Branch. Our designed PPG branch aims to produce the prior knowledge of physics. With utilizing the physics prior knowledge to guide the diffusion process, PDT branch can obtain underwater-aware ability and model the complex distribution in real-world underwater scenes. INR Branch can learn robust feature representations from diverse underwater image via implicit neural representation, which reduces the difficulty of restoration for PDT branch. Extensive experiments prove that our method achieves best performance on UIE tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement Zhao, Chen Dong, Chenyu Cai, Weiling Wang, Yueyue Computer Vision and Pattern Recognition Underwater visuals undergo various complex degradations, inevitably influencing the efficiency of underwater vision tasks. Recently, diffusion models were employed to underwater image enhancement (UIE) tasks, and gained SOTA performance. However, these methods fail to consider the physical properties and underwater imaging mechanisms in the diffusion process, limiting information completion capacity of diffusion models. In this paper, we introduce a novel UIE framework, named PA-Diff, designed to exploiting the knowledge of physics to guide the diffusion process. PA-Diff consists of Physics Prior Generation (PPG) Branch, Implicit Neural Reconstruction (INR) Branch, and Physics-aware Diffusion Transformer (PDT) Branch. Our designed PPG branch aims to produce the prior knowledge of physics. With utilizing the physics prior knowledge to guide the diffusion process, PDT branch can obtain underwater-aware ability and model the complex distribution in real-world underwater scenes. INR Branch can learn robust feature representations from diverse underwater image via implicit neural representation, which reduces the difficulty of restoration for PDT branch. Extensive experiments prove that our method achieves best performance on UIE tasks. |
| title | Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01497 |