Uformer: A General U-Shaped Transformer for Image Restoration

🤖 Plain-English Summary

In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. Without bells and whistles, our Uformer achieves superior or comparable performance compared with the advanced algorithms.

🔑 Key Findings

• In Uformer, there are two core designs.
• First, we introduce a novel locally-enhanced window (LeWin) Transformer block, which performs non-overlapping window-based self-attention instead of global self-attention.
• It significantly reduces the computational complexity on high resolution feature map while capturing local context.

🔗 Related Resources