Efficient Long-Range Attention Network for Image Super-resolution

By Xindong Zhang, Huiyu Zeng, Shi Guo, Lei Zhang. European Conference on Computer Vision, 2022

455 citations recorded by the source corpus.

Recently, transformer-based methods have demonstrated impressive results in various vision tasks, including image super-resolution (SR), by exploiting the self-attention (SA) for feature extraction. However, the computation of SA in most existing transformer based models is very expensive, while some employed operations may be redundant for the SR task. This limits the range of SA computation and consequently the SR performance. In this work, we propose an efficient long-range attention network (ELAN) for image SR. Specifically, we first employ shift convolution (shift-conv) to effectively extract the image local structural information while maintaining the same level of complexity as 1x1 convolution, then propose a group-wise multi-scale self-attention (GMSA) module, which calculates SA on non-overlapped groups of features using different window sizes to exploit the long-range image dependency. A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism. Without bells and whistles, our ELAN follows a fairly simple design by sequentially cascading the ELABs. Extensive experiments demonstrate that ELAN obtains even better results against the transformer-based SR models but with significantly less complexity. The source code can be found at https://github.com/xindongzhang/ELAN.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/71b646590bbc45f2d79bc9ca1251926beca02e7c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yulun Zhang
2. Jinjin Gu
3. Luc Van Gool
4. Radu Timofte
5. Fisher Yu
6. Lei Zhang
7. Chen Change Loy
8. Ming-Hsuan Yang

In Media Technology

1. Jinjin Gu
2. Zheng Chen
3. Fisher Yu
4. Xiaokang Yang
5. Yulun Zhang
6. L. Kong
7. Radu Timofte
8. Kai Zhang

Citations in the corpus

• Dual Aggregation Transformer for Image Super-Resolution (2023, methodology): “[29], SwinIR [13], and our DAT-S.”
• The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024, unknown): “YOLOv10 introduced groundbreaking innovations that enhanced performance and efficiency, building on the strengths of its predecessors while pushing the boundaries of real-time object detection.”
• SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (2023, unknown): “A variety of methods focusing on model design have been proposed [7– 10, 33, 36, 74–76] to improve the accuracy of ISR reconstruction.”