MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network
This addresses the challenge of denoising images with large noise for applications like photography or medical imaging, representing an incremental improvement over existing blind-spot network methods.
The paper tackles the problem of self-supervised image denoising for real-world images with large-scale spatially correlated noise, proposing MM-BSN, a method that uses a multi-mask strategy with blind-spot networks to break noise correlation and achieves state-of-the-art performance on public datasets without labels or prior knowledge.
Recent advances in deep learning have been pushing image denoising techniques to a new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most common methods. However, most of the existing BSN algorithms use a dot-based central mask, which is recognized as inefficient for images with large-scale spatially correlated noise. In this paper, we give the definition of large-noise and propose a multi-mask strategy using multiple convolutional kernels masked in different shapes to further break the noise spatial correlation. Furthermore, we propose a novel self-supervised image denoising method that combines the multi-mask strategy with BSN (MM-BSN). We show that different masks can cause significant performance differences, and the proposed MM-BSN can efficiently fuse the features extracted by multi-masked layers, while recovering the texture structures destroyed by multi-masking and information transmission. Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods. Extensive experiments on public real-world datasets demonstrate that the proposed MM-BSN achieves state-of-the-art performance among self-supervised and even unpaired image denoising methods for sRGB images denoising, without any labelling effort or prior knowledge. Code can be found in https://github.com/dannie125/MM-BSN.