SRFLOW‐Attention: Super Resolution with Multi‐Head Attention for Effective Use of Low‐Resolution Information
Authors:
- 25 April 2024
- journal article
- research article
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 19 (8) , 1360-1368
Abstract
This paper proposes normalizing flow‐based image super‐resolution techniques using attention modules. In the proposed method, the features of the low‐resolution images are extracted using a Swin Transformer. Furthermore, multi‐head attention in the flow layers makes effective use of the feature maps. This architecture enables the efficient injection of low‐resolution image features extracted by the transformer into the flow layer. Experimental results at x4 magnifications showed that the proposed method achieved state‐of‐the‐art performance for quantitative metrics and visual quality among single‐loss architectures. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.Keywords
Funding Information
- KAKENHI (JP21K11807)
This publication has 14 references indexed in Scilit:
- SwinIR: Image Restoration Using Swin Transformer2021
- SRFlow: Learning the Super-Resolution Space with Normalizing Flow2020
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Learning a Deep Convolutional Network for Image Super-Resolution2014
- On Single Image Scale-Up Using Sparse-Representations2012
- Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 2010
- Learning Low-Level VisionInternational Journal of Computer Vision, 2000