Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
Preprint
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 13 references indexed in Scilit:
- N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution2023
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- SwinIR: Image Restoration Using Swin Transformer2021
- Pre-Trained Image Processing Transformer2021
- LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block2020
- Single Image Super-Resolution via a Holistic Attention Network2020
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- Residual Dense Network for Image Super-Resolution2018
- On Single Image Scale-Up Using Sparse-Representations2012
- Single image super-resolution using Gaussian process regression2011