Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909542597525504 |
|---|---|
| author | Lan, Yunwei Cui, Zhigao Liu, Chang Peng, Jialun Wang, Nian Luo, Xin Liu, Dong |
| author_facet | Lan, Yunwei Cui, Zhigao Liu, Chang Peng, Jialun Wang, Nian Luo, Xin Liu, Dong |
| contents | Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method. Our code https://github.com/ywxjm/Diff-Dehazer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15017 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training Lan, Yunwei Cui, Zhigao Liu, Chang Peng, Jialun Wang, Nian Luo, Xin Liu, Dong Computer Vision and Pattern Recognition Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method. Our code https://github.com/ywxjm/Diff-Dehazer. |
| title | Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15017 |