UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior

2025-01-12

AI Summary

To address the degradation of detail preservation and restoration quality in real-world image dehazing caused by reliance on a single physical prior, this paper proposes an end-to-end unpaired dehazing method. The approach introduces three key innovations: (1) a Shared Prior Estimator (SPE) that jointly models multiple physical priors to mitigate prior bias; (2) Dynamic Wavelet-Separable Convolution (DWSC) for efficient multi-frequency feature fusion; and (3) an adaptive chromaticity corrector coupled with a self-supervised consistency loss to enhance color fidelity. Quantitatively, the method achieves state-of-the-art performance across PSNR, SSIM, LPIPS, FID, and CIEDE2000 metrics. Moreover, it significantly improves downstream object detection and semantic segmentation accuracy, demonstrating strong generalization capability and practical utility in real-world applications.

Technology Category

• Computer Vision: Segmentation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Image dehazing techniques aim to enhance contrast and restore details, which are essential for preserving visual information and improving image processing accuracy. Existing methods rely on a single manual prior, which cannot effectively reveal image details. To overcome this limitation, we propose an unpaired image dehazing network, called the Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior (UR2P-Dehaze). First, to accurately estimate the illumination, reflectance, and color information of the hazy image, we design a shared prior estimator (SPE) that is iteratively trained to ensure the consistency of illumination and reflectance, generating clear, high-quality images. Additionally, a self-monitoring mechanism is introduced to eliminate undesirable features, providing reliable priors for image reconstruction. Next, we propose Dynamic Wavelet Separable Convolution (DWSC), which effectively integrates key features across both low and high frequencies, significantly enhancing the preservation of image details and ensuring global consistency. Finally, to effectively restore the color information of the image, we propose an Adaptive Color Corrector that addresses the problem of unclear colors. The PSNR, SSIM, LPIPS, FID and CIEDE2000 metrics on the benchmark dataset show that our method achieves state-of-the-art performance. It also contributes to the performance improvement of downstream tasks. The project code will be available at https://github.com/Fan-pixel/UR2P-Dehaze. end{abstract}

Problem

• Dehazing
• Real-world Images
• Image Quality

Innovation

• UR2P-Dehaze
• Unsupervised Learning
• Image Dehazing