SwinIR: Image Restoration Using Swin Transformer
Abstrak
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 up to 0.14∼0.45dB, while the total number of parameters can be reduced by up to 67%.
Topik & Kata Kunci
Penulis (6)
Jingyun Liang
Jie Cao
Guolei Sun
K. Zhang
L. Gool
R. Timofte
Akses Cepat
- Tahun Terbit
- 2021
- Bahasa
- en
- Total Sitasi
- 4416×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/ICCVW54120.2021.00210
- Akses
- Open Access ✓