PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
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.
Code (1)
Tasks
Image DehazingSimilar Papers 제목 키워드 기반
PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing
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 DehazingHazeCLIP: Towards Language Guided Real-World Image Dehazing
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 DehazingGGADN: Guided generative adversarial dehazing network
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 DehazingVideo Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
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
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