Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
This addresses the lack of general-purpose blind denoising methods for real images, which is a practical problem for image processing applications, though it appears incremental as it builds on existing UNet and transformer architectures.
The paper tackles the problem of blind image denoising for real images by proposing a new network architecture (Swin-Conv-UNet) and a practical noise degradation model for training data synthesis, achieving state-of-the-art performance in experiments on AWGN removal and real image denoising.
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.