Original article was published on Artificial Intelligence on Medium
Reading: EDVR — Enhanced Deformable Convolutional Networks (Video Super Resolution)
In this story, Video Restoration with Enhanced Deformable Convolutional Networks (EDVR), by The Chinese University of Hong Kong, Nanyang Technological University, and Chinese Academy of Sciences, is presented. In this paper:
- A Pyramid, Cascading and Deformable (PCD) alignment module is used to align frames at feature level to handle large motions.
- A Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration.
- Finally, EDVR wins the champions and outperforms the second place by a large margin in all four tracks in the NTIRE19 video restoration and enhancement challenges.
This is a paper in 2019 CVPRW with over 50 citations. (Sik-Ho Tsang @ Medium)