Efficient Transformer for Single Image Super-Resolution

By Zhisheng Lu, Hong Liu, Juncheng Li, Linlin Zhang. 2021

69 citations recorded by the source corpus.

How researchers see this paper

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

1. Syed Waqas Zamir
2. Salman Hameed Khan
3. Fahad Shahbaz Khan
4. Munawar Hayat
5. Muzammal Naseer
6. Lei Zhang
7. Luc Van Gool
8. Ming-Hsuan Yang

Citations in the corpus

• Transformers in Vision: A Survey (2021, methodology): “Since the computational complexity of the original self-attention operation is prohibitively high for high-resolution images, recently a few efficient transformer models have been proposed that employ window-based attention (SwinIR [124]) and spatial resolution reduction operation in attention modul”
• Activating More Pixels in Image Super-Resolution Transformer (2022, unknown): “Due to the impressive performance, Transformer has also been introduced for low-level vision tasks [5,54,37,29,3,62,28,26].”
• Efficient Long-Range Attention Network for Image Super-resolution (2022, methodology): “We first compare our ELAN-light with state-of-the-art light-weight SR models, including CNN-based models CARN[2], IMDN [19], LAPAR-A[26], LatticeNet[38], and transformer-based models ESRT [37] and SwinIR-light[29].”