HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution

TL;DR

This paper introduces HiT-SR, a hierarchical transformer architecture for image super-resolution that enhances multi-scale feature extraction and long-range dependencies while maintaining computational efficiency, leading to state-of-the-art results.

Contribution

The paper proposes a hierarchical transformer design with expanding windows and a linear complexity spatial-channel correlation method for efficient, high-performance image super-resolution.

Findings

Achieves state-of-the-art SR performance with fewer parameters.

Faster processing speed, approximately 7 times quicker.

Effective multi-scale feature aggregation and long-range dependency modeling.

Abstract

Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computational complexity to window sizes, resulting in fixed small windows with limited receptive fields. In this paper, we present a general strategy to convert transformer-based SR networks to hierarchical transformers (HiT-SR), boosting SR performance with multi-scale features while maintaining an efficient design. Specifically, we first replace the commonly used fixed small windows with expanding hierarchical windows to aggregate features at different scales and establish long-range dependencies. Considering the intensive computation required for large windows, we further design a spatial-channel correlation method with linear complexity to window sizes, efficiently gathering spatial and channel information from hierarchical windows. Extensive experiments verify the effectiveness and efficiency of our HiT-SR, and our improved versions of SwinIR-Light, SwinIR-NG, and SRFormer-Light yield state-of-the-art SR results with fewer parameters, FLOPs, and faster speeds ($\sim7\times$).