Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
This work addresses a bottleneck in self-supervised denoising for image processing applications, offering a novel method that improves performance and efficiency over existing approaches.
The paper tackles the problem of self-supervised image denoising by proposing Noise2Same, a framework that introduces a new self-supervised loss derived from a supervised loss upper bound, eliminating the need for J-invariance and noise model information. The result shows that Noise2Same remarkably outperforms previous self-supervised methods in denoising performance and training efficiency.
Self-supervised frameworks that learn denoising models with merely individual noisy images have shown strong capability and promising performance in various image denoising tasks. Existing self-supervised denoising frameworks are mostly built upon the same theoretical foundation, where the denoising models are required to be J-invariant. However, our analyses indicate that the current theory and the J-invariance may lead to denoising models with reduced performance. In this work, we introduce Noise2Same, a novel self-supervised denoising framework. In Noise2Same, a new self-supervised loss is proposed by deriving a self-supervised upper bound of the typical supervised loss. In particular, Noise2Same requires neither J-invariance nor extra information about the noise model and can be used in a wider range of denoising applications. We analyze our proposed Noise2Same both theoretically and experimentally. The experimental results show that our Noise2Same remarkably outperforms previous self-supervised denoising methods in terms of denoising performance and training efficiency. Our code is available at https://github.com/divelab/Noise2Same.