Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
This work addresses a key bottleneck in super-resolution for computer vision applications, though it appears incremental as it builds on existing transformer-based approaches.
The paper tackles the limited receptive field in window-based self-attention for single image super-resolution by introducing an Adaptive Token Dictionary method, achieving state-of-the-art performance on various benchmarks.
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.