JingyunLiang/SwinIR
SwinIR is a PyTorch implementation of a Swin Transformer-based model for image restoration including super-resolution, denoising, and compression artifact removal.

Velocity · 7d
+3.1
★ / day
Trend
→steady
star history
This repository provides the official implementation of SwinIR, an image restoration framework that leverages shifted window-based transformers for low-level vision tasks. It covers classical image super-resolution, image denoising, and compression artifact reduction. The model uses Swin Transformer blocks to capture local and global features for高质量图像恢复。