Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework

TL;DR

This paper introduces ZS-NCD, a neural compression-based zero-shot denoising method that optimizes on single noisy images, achieving state-of-the-art results and providing new theoretical error bounds.

Contribution

The work presents a novel neural compression framework for zero-shot denoising, with theoretical analysis and practical algorithms that outperform existing methods.

Findings

Achieves state-of-the-art zero-shot denoising performance.

Effectively handles Gaussian and Poisson noise.

Generalizes well to various image types.

Abstract

Zero-shot denoising aims to denoise observations without access to training samples or clean reference images. This setting is particularly relevant in practical imaging scenarios involving specialized domains such as medical imaging or biology. In this work, we propose the Zero-Shot Neural Compression Denoiser (ZS-NCD), a novel denoising framework based on neural compression. ZS-NCD treats a neural compression network as an untrained model, optimized directly on patches extracted from a single noisy image. The final reconstruction is then obtained by aggregating the outputs of the trained model over overlapping patches. Thanks to the built-in entropy constraints of compression architectures, our method naturally avoids overfitting and does not require manual regularization or early stopping. Through extensive experiments, we show that ZS-NCD achieves state-of-the-art performance among zero-shot denoisers for both Gaussian and Poisson noise, and generalizes well to both natural and non-natural images. Additionally, we provide new finite-sample theoretical results that characterize upper bounds on the achievable reconstruction error of general maximum-likelihood compression-based denoisers. These results further establish the theoretical foundations of compression-based denoising. Our code is available at: https://github.com/Computational-Imaging-RU/ZS-NCDenoiser.