Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising

TL;DR

This paper introduces Positive2Negative, a self-supervised single image denoising method that preserves information and achieves state-of-the-art results by constructing multiple denoised images without information loss.

Contribution

The paper proposes a novel paradigm that overcomes information loss in self-supervised denoising by using renoised data construction and denoised consistency supervision.

Findings

Achieves state-of-the-art denoising performance.

Significantly faster than existing methods.

Preserves all original image information.

Abstract

Image denoising enhances image quality, serving as a foundational technique across various computational photography applications. The obstacle to clean image acquisition in real scenarios necessitates the development of self-supervised image denoising methods only depending on noisy images, especially a single noisy image. Existing self-supervised image denoising paradigms (Noise2Noise and Noise2Void) rely heavily on information-lossy operations, such as downsampling and masking, culminating in low quality denoising performance. In this paper, we propose a novel self-supervised single image denoising paradigm, Positive2Negative, to break the information-lossy barrier. Our paradigm involves two key steps: Renoised Data Construction (RDC) and Denoised Consistency Supervision (DCS). RDC renoises the predicted denoised image by the predicted noise to construct multiple noisy images, preserving all the information of the original image. DCS ensures consistency across the multiple denoised images, supervising the network to learn robust denoising. Our Positive2Negative paradigm achieves state-of-the-art performance in self-supervised single image denoising with significant speed improvements. The code is released to the public at https://github.com/Li-Tong-621/P2N.