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.
翻译:近年来深度学习的发展使图像去噪技术又迈上了新的台阶。在自监督图像去噪技术方面,盲点网络是最常用的方法之一。然而,大部分现有的盲点网络算法都使用一个基于点的中央掩模,在存在大规模有空间相关的噪声的图像上,该方法效率低下。在本文中,我们给出了大噪声的定义,并提出了基于多卷积核掩膜以打破空间相关性的多掩模策略。此外,我们提出了一种新颖的自监督图像去噪方法,将多掩模策略与盲点网络相结合,称为MM-BSN。我们证明了不同的掩模会导致显著的性能差异,并且MM-BSN可以有效地融合多个掩膜层提取的特征,同时恢复被多重掩膜破坏的纹理结构和信息传输。我们的MM-BSN可用于解决其他BSN方法无法有效处理的大噪声去噪问题。公开的真实数据集上的大量实验表明,所提出的MM-BSN在sRGB图像去噪方面在自监督和甚至无配对图像去噪方法中均取得了最佳性能,而无需任何标签工作或先验知识。代码可在https://github.com/dannie125/MM-BSN中找到。