Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

by   Zejin Wang, et al.

Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data collection problem. However, self-supervised denoising methods, especially blindspot-driven ones, suffer sizable information loss during input or network design. The absence of valuable information dramatically reduces the upper bound of denoising performance. In this paper, we propose a simple yet efficient approach called Blind2Unblind to overcome the information loss in blindspot-driven denoising methods. First, we introduce a global-aware mask mapper that enables global perception and accelerates training. The mask mapper samples all pixels at blind spots on denoised volumes and maps them to the same channel, allowing the loss function to optimize all blind spots at once. Second, we propose a re-visible loss to train the denoising network and make blind spots visible. The denoiser can learn directly from raw noise images without losing information or being trapped in identity mapping. We also theoretically analyze the convergence of the re-visible loss. Extensive experiments on synthetic and real-world datasets demonstrate the superior performance of our approach compared to previous work. Code is available at


page 4

page 5

page 6

page 7

page 8

page 11

page 12


Blind2Sound: Self-Supervised Image Denoising without Residual Noise

Self-supervised blind denoising for Poisson-Gaussian noise remains a cha...

Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising

Self-supervised frameworks that learn denoising models with merely indiv...

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

Recent advances in deep learning have been pushing image denoising techn...

LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising

Despite the significant results on synthetic noise under simplified assu...

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

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

Recurrent Self-Supervised Video Denoising with Denser Receptive Field

Self-supervised video denoising has seen decent progress through the use...

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

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

Please sign up or login with your details

Forgot password? Click here to reset