paper-with-me

홈 › Papers

PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors

2021-06-19 · CVPR 2021 1 · Zeyuan Chen, Yangchao Wang, Yang Yang, Dong Liu

Deep learning-based methods have achieved remarkable performance for image dehazing. However, previous studies are mostly focused on training models with synthetic hazy images, which incurs performance drop when the models are used for real-world hazy images. We propose a Principled Synthetic-to-real Dehazing (PSD) framework to improve the generalization performance of dehazing. Starting from a dehazing model backbone that is pre-trained on synthetic data, PSD exploits real hazy images to fine-tune the model in an unsupervised fashion. For the fine-tuning, we leverage several well-grounded physical priors and combine them into a prior loss committee. PSD allows for most of the existing dehazing models as its backbone, and the combination of multiple physical priors boosts dehazing significantly. Through extensive experiments, we demonstrate that our PSD framework establishes the new state-of-the-art performance for real-world dehazing, in terms of visual quality assessed by no-reference quality metrics as well as subjective evaluation and downstream task performance indicator.

📄 PDF Abstract BibTeX

Code (1)

zychen-ustc/PSD-Principled-Synthetic-to-Real-Dehazing-Guided-by-Physical-Priors 공식 구현 pytorch

Tasks

Image Dehazing

Similar Papers 제목 키워드 기반

PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing

2024-04-14 · Chih-Ling Chang, Fu-Jen Tsai, Zi-Ling Huang, Lin Gu 외

Image dehazing faces challenges when dealing with hazy images in real-world scenarios. A huge domain gap between synthetic and real-world haze images degrades dehazing performance in practical settings. However, collecti…

Image Dehazing

HazeCLIP: Towards Language Guided Real-World Image Dehazing

2024-07-18 · Ruiyi Wang, Wenhao Li, Xiaohong Liu, Chunyi Li 외

Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets. However, they often struggle with real-world hazy images due to domain shift, limiting their practical applicab…

Image DehazingImage Quality AssessmentSingle Image Dehazing

GGADN: Guided generative adversarial dehazing network

2021-07-13 · journal 2021 7 · Jian Zhang1 · Qinqin Dong2 · Wanjuan Song3

Image dehazing has always been a challenging topic in image processing. The development of deep learning methods, especially the generative adversarial networks (GAN), provides a new way for image dehazing. In recent ye…

Image Dehazing

Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior

2023-03-17 · CVPR 2023 1 · Jiaqi Xu, Xiaowei Hu, Lei Zhu, Qi Dou 외

Video dehazing aims to recover haze-free frames with high visibility and contrast. This paper presents a novel framework to effectively explore the physical haze priors and aggregate temporal information. Specifically, w…

From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data

2021-08-06 · Ye Liu, Lei Zhu, Shunda Pei, Huazhu Fu 외

Single image dehazing is a challenging task, for which the domain shift between synthetic training data and real-world testing images usually leads to degradation of existing methods. To address this issue, we propose a …

Image DehazingSingle Image Dehazing