Decay2Distill: Leveraging spatial perturbation and regularization for self-supervised image denoising
This addresses the problem of image denoising without paired data or noise assumptions, offering a more practical solution for applications in computer vision.
The paper tackles unpaired image denoising by proposing a self-supervised method based on spatial degradation and regularized refinement, achieving robust performance across different data domains with considerable improvement over previous methods.
Unpaired image denoising has achieved promising development over the last few years. Regardless of the performance, methods tend to heavily rely on underlying noise properties or any assumption which is not always practical. Alternatively, if we can ground the problem from a structural perspective rather than noise statistics, we can achieve a more robust solution. with such motivation, we propose a self-supervised denoising scheme that is unpaired and relies on spatial degradation followed by a regularized refinement. Our method shows considerable improvement over previous methods and exhibited consistent performance over different data domains.