Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond

TL;DR

This paper introduces a hierarchical invertible neural network that disentangles noise from high-frequency image components, enabling effective denoising and artifact removal with reduced computational cost.

Contribution

It proposes a novel hierarchical disentangling framework within invertible neural networks for image denoising and artifact removal, emphasizing high-frequency noise separation.

Findings

Achieves competitive results on real image denoising tasks

Effective in JPEG artifact removal and low-dose CT image restoration

Reduces computational cost compared to existing methods

Abstract

Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, the implicit bijective mapping is not explored well. Inspired by a latent observation that noise tends to appear in the high-frequency part of the image, we propose a fully invertible denoising method that injects the idea of disentangled learning into a general invertible neural network to split noise from the high-frequency part. More specifically, we decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation and then disentangle case-specific noise and high-frequency components in the latent space. In this way, denoising is made tractable by inversely merging noiseless low and high-frequency parts. Furthermore, we construct a flexible hierarchical disentangling framework, which aims to decompose most of the low-frequency image information while disentangling noise from the high-frequency part in a coarse-to-fine manner. Extensive experiments on real image denoising, JPEG compressed artifact removal, and medical low-dose CT image restoration have demonstrated that the proposed method achieves competing performance on both quantitative metrics and visual quality, with significantly less computational cost.