MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network

by   Dan Zhang, et al.

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


page 1

page 3

page 5

page 6

page 7

page 8


Random Sub-Samples Generation for Self-Supervised Real Image Denoising

With sufficient paired training samples, the supervised deep learning me...

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

Real noisy-clean pairs on a large scale are costly and difficult to obta...

Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer

In recent years, the development of deep learning has been pushing image...

Explainable Artificial Intelligence driven mask design for self-supervised seismic denoising

The presence of coherent noise in seismic data leads to errors and uncer...

Mask-GVAE: Blind Denoising Graphs via Partition

We present Mask-GVAE, a variational generative model for blind denoising...

Exploring Asymmetric Tunable Blind-Spots for Self-supervised Denoising in Real-World Scenarios

Self-supervised denoising has attracted widespread attention due to its ...

View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution

In recent years, self-supervised denoising methods have shown impressive...

Please sign up or login with your details

Forgot password? Click here to reset