2020/10/22 by Yaochen Xie, Zhengyang Wang, Xie, Yaochen +3 · 7 citations
Computer Science · Engineering · #Image Processing Techniques and Applications #Image and Signal Denoising Methods #Photoacoustic and Ultrasonic Imaging #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2010.11971
15 pages, NeurIPS 2020
arxiv created 2020/10/22 · arxiv updated 2020/10/26
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.