Image Denoising via Style Disentanglement

TL;DR

This paper introduces a novel image denoising method that models noise as a style, enabling effective noise removal through style disentanglement, with improved interpretability and performance on synthetic and real datasets.

Contribution

We propose a style disentanglement approach for image denoising that explicitly separates noise styles from content, providing a clear denoising mechanism and interpretability.

Findings

Effective noise removal on synthetic and real datasets

Improved PSNR and SSIM metrics

Enhanced interpretability of the denoising process

Abstract

Image denoising is a fundamental task in low-level computer vision. While recent deep learning-based image denoising methods have achieved impressive performance, they are black-box models and the underlying denoising principle remains unclear. In this paper, we propose a novel approach to image denoising that offers both clear denoising mechanism and good performance. We view noise as a type of image style and remove it by incorporating noise-free styles derived from clean images. To achieve this, we design novel losses and network modules to extract noisy styles from noisy images and noise-free styles from clean images. The noise-free style induces low-response activations for noise features and high-response activations for content features in the feature space. This leads to the separation of clean contents from noise, effectively denoising the image. Unlike disentanglement-based image editing tasks that edit semantic-level attributes using styles, our main contribution lies in editing pixel-level attributes through global noise-free styles. We conduct extensive experiments on synthetic noise removal and real-world image denoising datasets (SIDD and DND), demonstrating the effectiveness of our method in terms of both PSNR and SSIM metrics. Moreover, we experimentally validate that our method offers good interpretability.