Deformable Non-Local Network for Video Super-Resolution

Deformable Non-Local Network for Video Super-Resolution

The video super-resolution (VSR) task aims to restore a high-resolution (HR) video frame by using its corresponding low-resolution (LR) frame and multiple neighboring frames. At present, many deep learning-based VSR methods rely on optical flow to perform frame alignment. The final recovery results...

Full description

Bibliographic Details
Main Authors: Hua Wang, Dewei Su, Chuangchuang Liu, Longcun Jin, Xianfang Sun, Xinyi Peng
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Convolutional neural networks
deep learning
deformable convolution
non-local operation
video super-resolution
Online Access:https://ieeexplore.ieee.org/document/8926405/

Internet

https://ieeexplore.ieee.org/document/8926405/

Similar Items