Learning Implicit Neural Degradation Representation for Unpaired Image Dehazing

TL;DR

This paper introduces an unsupervised implicit neural approach for image dehazing that models haze as a continuous function, improving performance in complex scenes without relying on explicit physical models.

Contribution

It proposes a novel implicit neural degradation representation for unpaired image dehazing, combining channel mechanisms inspired by Kolmogorov-Arnold theorem to enhance nonlinear dependency learning.

Findings

Achieves competitive dehazing results on public datasets

Effectively models haze as a continuous function eliminating explicit features

Enhances visual perception in complex scenes

Abstract

Image dehazing is an important task in the field of computer vision, aiming at restoring clear and detail-rich visual content from haze-affected images. However, when dealing with complex scenes, existing methods often struggle to strike a balance between fine-grained feature representation of inhomogeneous haze distribution and global consistency modeling. Furthermore, to better learn the common degenerate representation of haze in spatial variations, we propose an unsupervised dehaze method for implicit neural degradation representation. Firstly, inspired by the Kolmogorov-Arnold representation theorem, we propose a mechanism combining the channel-independent and channel-dependent mechanisms, which efficiently enhances the ability to learn from nonlinear dependencies. which in turn achieves good visual perception in complex scenes. Moreover, we design an implicit neural representation to model haze degradation as a continuous function to eliminate redundant information and the dependence on explicit feature extraction and physical models. To further learn the implicit representation of the haze features, we also designed a dense residual enhancement module from it to eliminate redundant information. This achieves high-quality image restoration. Experimental results show that our method achieves competitive dehaze performance on various public and real-world datasets. This project code will be available at https://github.com/Fan-pixel/NeDR-Dehaze.