Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis

Abstract

While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research.

arXiv commentCodes: https://github.com/cszn/SCUNet

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• LocalViT: Analyzing Locality in Vision Transformers
• Non-Local Recurrent Network for Image Restoration
• Variational Denoising Network: Toward Blind Noise Modeling and Removal
• Residual Non-local Attention Networks for Image Restoration
• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

Cited by in corpus (6)

• Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
• Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
• Enhancing kelp forest detection in remote sensing images using crowdsourced labels with Mixed Vision Transformers and ConvNeXt segmentation models
• DeepExtractor: Time-domain reconstruction of signals and glitches in gravitational wave data with deep learning
• Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
• FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising