PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tsai, Fu-Jen, Peng, Yan-Tsung, Lin, Yen-Yu, Lin, Chia-Wen
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