PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909696747634688 |
|---|---|
| author | Tsai, Fu-Jen Peng, Yan-Tsung Lin, Yen-Yu Lin, Chia-Wen |
| author_facet | Tsai, Fu-Jen Peng, Yan-Tsung Lin, Yen-Yu Lin, Chia-Wen |
| contents | Image dehazing aims to remove unwanted hazy artifacts in images. Although previous research has collected paired real-world hazy and haze-free images to improve dehazing models' performance in real-world scenarios, these models often experience significant performance drops when handling unseen real-world hazy images due to limited training data. This issue motivates us to develop a flexible domain adaptation method to enhance dehazing performance during testing. Observing that predicting haze patterns is generally easier than recovering clean content, we propose the Physics-guided Haze Transfer Network (PHATNet) which transfers haze patterns from unseen target domains to source-domain haze-free images, creating domain-specific fine-tuning sets to update dehazing models for effective domain adaptation. Additionally, we introduce a Haze-Transfer-Consistency loss and a Content-Leakage Loss to enhance PHATNet's disentanglement ability. Experimental results demonstrate that PHATNet significantly boosts state-of-the-art dehazing models on benchmark real-world image dehazing datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing Tsai, Fu-Jen Peng, Yan-Tsung Lin, Yen-Yu Lin, Chia-Wen Computer Vision and Pattern Recognition Image dehazing aims to remove unwanted hazy artifacts in images. Although previous research has collected paired real-world hazy and haze-free images to improve dehazing models' performance in real-world scenarios, these models often experience significant performance drops when handling unseen real-world hazy images due to limited training data. This issue motivates us to develop a flexible domain adaptation method to enhance dehazing performance during testing. Observing that predicting haze patterns is generally easier than recovering clean content, we propose the Physics-guided Haze Transfer Network (PHATNet) which transfers haze patterns from unseen target domains to source-domain haze-free images, creating domain-specific fine-tuning sets to update dehazing models for effective domain adaptation. Additionally, we introduce a Haze-Transfer-Consistency loss and a Content-Leakage Loss to enhance PHATNet's disentanglement ability. Experimental results demonstrate that PHATNet significantly boosts state-of-the-art dehazing models on benchmark real-world image dehazing datasets. |
| title | PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14826 |