HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computational complexity to window sizes, resulting in fixed small windows with limited receptive fields. In this paper, we present a general strategy to convert transformer-based SR networks to hierarchical transformers (HiT-SR), boosting SR performance with multi-scale features while maintaining an efficient design. Specifically, we first replace the commonly used fixed small windows with expanding hierarchical windows to aggregate features at different scales and establish long-range dependencies. Considering the intensive computation required for large windows, we further design a spatial-channel correlation method with linear complexity to window sizes, efficiently gathering spatial and channel information from hierarchical windows. Extensive experiments verify the effectiveness and efficiency of our HiT-SR, and our improved versions of SwinIR-Light, SwinIR-NG, and SRFormer-Light yield state-of-the-art SR results with fewer parameters, FLOPs, and faster speeds ($\sim7\times$).
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
HST: Hierarchical Swin Transformer for Compressed Image Super-resolution
Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to resto…
Compressed Image Super-resolutionImage Super-ResolutionSuper-ResolutionMulti-granularity Backprojection Transformer for Remote Sensing Image Super-Resolution
Backprojection networks have achieved promising super-resolution performance for nature images but not well be explored in the remote sensing image super-resolution (RSISR) field due to the high computation costs. In thi…
Image ReconstructionImage Super-ResolutionSuper-ResolutionScaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. - 256x256, 384…
Self-Supervised LearningSurvival PredictionCogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and l…
Image GenerationLanguage ModelingLanguage ModellingSuper-Resolution+2MaxSR: Image Super-Resolution Using Improved MaxViT
While transformer models have been demonstrated to be effective for natural language processing tasks and high-level vision tasks, only a few attempts have been made to use powerful transformer models for single image su…
Image Super-ResolutionSuper-Resolution