Self-Verification in Image Denoising

TL;DR

This paper introduces self-verification regularization for image denoising, enabling a self-supervised learning approach that achieves near-supervised performance without requiring clean images.

Contribution

It proposes a novel self-verification regularization using deep image priors, allowing effective self-supervised denoising that bridges traditional and learning-based methods.

Findings

Achieves denoising performance close to supervised CNNs.

Enables learning without access to clean images.

Demonstrates effectiveness across various denoising tasks.

Abstract

We devise a new regularization, called self-verification, for image denoising. This regularization is formulated using a deep image prior learned by the network, rather than a traditional predefined prior. Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''. The comparison between the again denoised image and its prior can be interpreted as a self-verification of the network's denoising ability. We demonstrate that self-verification encourages the network to capture low-level image statistics needed to restore the image. Based on this self-verification regularization, we further show that the network can learn to denoise even if it has not seen any clean images. This learning strategy is self-supervised, and we refer to it as Self-Verification Image Denoising (SVID). SVID can be seen as a mixture of learning-based methods and traditional model-based denoising methods, in which regularization is adaptively formulated using the output of the network. We show the application of SVID to various denoising tasks using only observed corrupted data. It can achieve the denoising performance close to supervised CNNs.