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

by   Shiyan Chen, et al.

Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms based on the pixel-wise independent noise assumption to perform poorly on real-world images. Recently, asymmetric pixel-shuffle downsampling (AP) has been proposed to disrupt the spatial correlation of noise. However, downsampling introduces aliasing effects, and the post-processing to eliminate these effects can destroy the spatial structure and high-frequency details of the image, in addition to being time-consuming. In this paper, we systematically analyze downsampling-based methods and propose an Asymmetric Tunable Blind-Spot Network (AT-BSN) to address these issues. We design a blind-spot network with a freely tunable blind-spot size, using a large blind-spot during training to suppress local spatially correlated noise while minimizing damage to the global structure, and a small blind-spot during inference to minimize information loss. Moreover, we propose blind-spot self-ensemble and distillation of non-blind-spot network to further improve performance and reduce computational complexity. Experimental results demonstrate that our method achieves state-of-the-art results while comprehensively outperforming other self-supervised methods in terms of image texture maintaining, parameter count, computation cost, and inference time.


page 1

page 3

page 4

page 6


I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images

Although the advances of self-supervised blind denoising are significant...

Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network

There have been many image denoisers using deep neural networks, which o...

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network

Blind-spot network (BSN) and its variants have made significant advances...

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...

SS-BSN: Attentive Blind-Spot Network for Self-Supervised Denoising with Nonlocal Self-Similarity

Recently, numerous studies have been conducted on supervised learning-ba...

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

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

A Regularization Approach to Blind Deblurring and Denoising of QR Barcodes

QR bar codes are prototypical images for which part of the image is a pr...

Please sign up or login with your details

Forgot password? Click here to reset