A Topological Loss Function: Image Denoising on a Low-Light Dataset

TL;DR

This paper introduces a novel topological loss function based on persistent homology for image denoising, specifically targeting real low-light images, and demonstrates its superior performance over existing methods.

Contribution

The paper proposes a new topological loss function using persistent homology for image denoising, evaluated on a new low-light dataset, improving structure preservation and artifact suppression.

Findings

Outperforms existing denoising methods on low-light images

Adapts well to complex image structures

Reduces common denoising artifacts

Abstract

Although image denoising algorithms have attracted significant research attention, surprisingly few have been proposed for, or evaluated on, noise from imagery acquired under real low-light conditions. Moreover, noise characteristics are often assumed to be spatially invariant, leading to edges and textures being distorted after denoising. Here, we introduce a novel topological loss function which is based on persistent homology. The method performs in the space of image patches, where topological invariants are calculated and represented in persistent diagrams. The loss function is a combination of $\ell_1$ or $\ell_2$ losses with the new persistence-based topological loss. We compare its performance across popular denoising architectures and loss functions, training the networks on our new comprehensive dataset of natural images captured in low-light conditions -- BVI-LOWLIGHT. Analysis reveals that this approach outperforms existing methods, adapting well to complex structures and suppressing common artifacts.