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

TL;DR

This paper introduces a novel network architecture combining Swin transformer and convolutional layers within a UNet framework, along with a comprehensive noise synthesis model, to improve blind image denoising for real-world images.

Contribution

It proposes a Swin-Conv-UNet architecture and a versatile noise synthesis method to enhance blind denoising performance on real images.

Findings

Achieves state-of-the-art results in blind denoising tasks.

Effectively models various real-world noise types.

Improves practical denoising performance with the new data synthesis strategy.

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.