Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
Authors:
Top Cited Papers
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2856-2865
Abstract
Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have seen significant advancements in recent years, challenges still remain, particularly in limited receptive field caused by window-based self-attention. To address these issues, we introduce a group of auxiliary Adaptive Token Dictionary to SR Transformer and establish an ATD-SR method. The introduced token dictionary could learn prior information from training data and adapt the learned prior to specific testing image through an adaptive refinement step. The refinement strategy could not only provide global information to all input tokens but also group image tokens into categories. Based on category partitions, we further propose a category-based self-attention mechanism designed to leverage distant but similar tokens for enhancing input features. The experimental results show that our method achieves the best performance on various single image super-resolution benchmarks.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Efficient Long-Range Attention Network for Image Super-Resolution2022
- LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block2020
- Single Image Super-Resolution via a Holistic Attention Network2020
- Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network2018
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Single image super-resolution from transformed self-exemplars2015
- On Single Image Scale-Up Using Sparse-Representations2012
- Single image super-resolution using Gaussian process regression2011