Super-resolution video using non-neighboring frames without frame alignment

Super-resolution video using non-neighboring frames without frame alignment

Memory-Augmented Non-Local Attention for Video Super-Resolution

arXiv paper abstract https://arxiv.org/abs/2108.11048v1

arXiv PDF paper https://arxiv.org/pdf/2108.11048v1.pdf

In this paper, we propose a novel video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones.

Previous methods predominantly leverage temporal neighbor frames

... suffer from the challenge in spatial frame alignment and the lack of useful information from similar LR neighbor frames.

... we devise a cross-frame non-local attention mechanism that allows video super-resolution without frame alignment

... In addition, to acquire the information beyond neighbor frames, we ... memorize general video details during the super-resolution training.

... method can achieve superior performance on large motion videos comparing to the state-of-the-art methods without aligning frames. ...

Please like and share this post if you enjoyed it using the buttons at the bottom! 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 #ComputerVision #SuperResolution #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning