Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image

Abstract

Supervised deep networks have achieved promisingperformance on image denoising, by learning image priors andnoise statistics on plenty pairs of noisy and clean images. Unsupervised denoising networks are trained with only noisy images. However, for an unseen corrupted image, both supervised andunsupervised networks ignore either its particular image prior, the noise statistics, or both. That is, the networks learned from external images inherently suffer from a domain gap problem: the image priors and noise statistics are very different between the training and test images. This problem becomes more clear when dealing with the signal dependent realistic noise. To circumvent this problem, in this work, we propose a novel "Noisy-As-Clean" (NAC) strategy of training self-supervised denoising networks. Specifically, the corrupted test image is directly taken as the "clean" target, while the inputs are synthetic images consisted of this corrupted image and a second and similar corruption. A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images. Experiments on synthetic and realistic noise removal demonstrate that, the DnCNN and ResNet networks trained with our self-supervised NAC strategy achieve comparable or better performance than the original ones and previous supervised/unsupervised/self-supervised networks. The code is publicly available at https://github.com/csjunxu/Noisy-As-Clean.

12 pages, 9 figures, 6 tables, the first two authors contribute equally

References in corpus (6)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• STAR: A Structure and Texture Aware Retinex Model
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Conditional Variational Image Deraining
• NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoising

Cited by in corpus (11)

• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation
• Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
• Optimal Transport for Unsupervised Denoising Learning
• Weak-signal extraction enabled by deep-neural-network denoising of diffraction data
• CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise
• Zero-Shot Image Denoising for High-Resolution Electron Microscopy
• Automatic Tuning of Denoising Algorithms Parameters Without Ground Truth
• Reinforcement Learning of Self Enhancing Camera Image and Signal Processing
• MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data
• FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising
• Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing