DRCT: Saving Image Super-resolution away from Information Bottleneck

arXiv:2404.00722v1 Announce Type: new
Abstract: In recent years, Vision Transformer-based applications to low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of images utilizing information from non-local areas. In the domain of super-resolution, Swin-transformer-based approaches have become mainstream due to their capacity to capture global spatial information and their shifting-window attention mechanism that facilitates the interchange of information between different windows. Many researchers have enhanced image quality and …

abstract adept applications arxiv become cnn cs.ai cs.cv dependencies domain enabling image images information low resolution saving success swin tasks transformer transformers type vision