Deep Variation Prior: Joint Image Denoising and Noise Variance Estimation without Clean Data

TL;DR

This paper introduces a joint unsupervised deep learning framework that simultaneously denoises images and estimates noise variance without needing clean data, leveraging a novel variation prior to address the ill-posedness of the problem.

Contribution

It proposes the deep variation prior (DVP) to guide unsupervised learning of denoisers and noise variance estimation in a unified framework, eliminating the need for clean images or external noise estimation.

Findings

Achieves denoising performance comparable to supervised methods.

Accurately estimates noise variances from noisy images.

Operates without requiring clean training data.

Abstract

With recent deep learning based approaches showing promising results in removing noise from images, the best denoising performance has been reported in a supervised learning setup that requires a large set of paired noisy images and ground truth for training. The strong data requirement can be mitigated by unsupervised learning techniques, however, accurate modelling of images or noise variance is still crucial for high-quality solutions. The learning problem is ill-posed for unknown noise distributions. This paper investigates the tasks of image denoising and noise variance estimation in a single, joint learning framework. To address the ill-posedness of the problem, we present deep variation prior (DVP), which states that the variation of a properly learnt denoiser with respect to the change of noise satisfies some smoothness properties, as a key criterion for good denoisers. Building upon DVP, an unsupervised deep learning framework, that simultaneously learns a denoiser and estimates noise variances, is developed. Our method does not require any clean training images or an external step of noise estimation, and instead, approximates the minimum mean squared error denoisers using only a set of noisy images. With the two underlying tasks being considered in a single framework, we allow them to be optimised for each other. The experimental results show a denoising quality comparable to that of supervised learning and accurate noise variance estimates.