Semantic Scholar Open Access 2021 4416 sitasi

SwinIR: Image Restoration Using Swin Transformer

Jingyun Liang Jie Cao Guolei Sun K. Zhang L. Gool +1 lainnya

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%.

Penulis (6)

J

Jingyun Liang

J

Jie Cao

G

Guolei Sun

K

K. Zhang

L

L. Gool

R

R. Timofte

Format Sitasi

Liang, J., Cao, J., Sun, G., Zhang, K., Gool, L., Timofte, R. (2021). SwinIR: Image Restoration Using Swin Transformer. https://doi.org/10.1109/ICCVW54120.2021.00210

Akses Cepat

Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
4416×
Sumber Database
Semantic Scholar
DOI
10.1109/ICCVW54120.2021.00210
Akses
Open Access ✓