SwinIR: Image Restoration Using Swin Transformer
arXiv:2108.10257
Abstract
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by $\textbf{up to 0.14$\sim$0.45dB}$, while the total number of parameters can be reduced by $\textbf{up to 67%}$.
arXiv commentSota results on classical/lightweight/real-world image SR, image denoising and JPEG compression artifact reduction. Code: https://github.com/JingyunLiang/SwinIR
References in corpus (18)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Sketch-based Manga Retrieval using Manga109 Dataset
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision
- Early Convolutions Help Transformers See Better
- LocalViT: Analyzing Locality in Vision Transformers
- Non-Local Recurrent Network for Image Restoration
- Stand-Alone Self-Attention in Vision Models
- Video Super-Resolution Transformer
- Cross-Scale Internal Graph Neural Network for Image Super-Resolution
- Uformer: A General U-Shaped Transformer for Image Restoration
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
- Neural Nearest Neighbors Networks
- Rethinking Global Context in Crowd Counting
- Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution