Super-resolution video using continuity between frames and previous results with MIA-VSR
Super-resolution video using continuity between frames and previous results with MIA-VSR
Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention
arXiv paper abstract https://arxiv.org/abs/2401.06312
arXiv PDF paper https://arxiv.org/pdf/2401.06312.pdf
… Vision Transformer has … great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task. Despite its superiority … the heavy computational … as well as the large memory footprint hinder the deployment of Transformer-based
… proposing a novel feature-level masked processing framework: VSR with Masked Intra and inter frame Attention (MIA-VSR).
… MIA-VSR is leveraging feature-level temporal continuity between adjacent frames to reduce redundant computations and … use of previously enhanced SR features.
… propose an intra-frame and inter-frame attention block which takes the respective roles of past features and input features into consideration and only exploits previously enhanced features to provide supplementary information.
… adaptive block-wise mask prediction module is developed to skip unimportant computations according to feature similarity between adjacent frames.
… MIA-VSR improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
