Transformer for super-resolution video
Transformer for super-resolution video
Video Super-Resolution Transformer
arXiv paper abstract https://arxiv.org/abs/2106.06847
arXiv PDF paper https://arxiv.org/pdf/2106.06847.pdf
Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version
... make the first attempt to adapt Transformer for VSR.
... we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information.
... we design a bidirectional optical flow-based feed-forward layer to discover the correlations across different video frames and also align features.
Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. ...
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
Comments