4.1 Article

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

期刊

MACHINE INTELLIGENCE RESEARCH
卷 -, 期 -, 页码 -

出版社

SPRINGERNATURE
DOI: 10.1007/s11633-023-1466-0

关键词

Blind image denoising; real image denosing data synthesis; Transformer; image signal processing (ISP) pipeline

向作者/读者索取更多资源

This paper proposes a new approach for image denoising by focusing on network architecture design and training data synthesis. The use of a swin-conv block in the image-to-image translation UNet architecture significantly improves denoising performance. Additionally, a practical noise degradation model is designed to handle various types of noise and resizing, leading to improved practicality. Experimental results demonstrate the effectiveness of the proposed methods.
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. The source code is available at https://github.com/cszn/SCUNet.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.1
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据