Video Super-Resolution With Temporal Group Attention
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8005-8014
Abstract
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate temporal information in a hierarchical way. The input sequence is divided into several groups, with each one corresponding to a kind of frame rate. These groups provide complementary information to recover missing details in the reference frame, which is further integrated with an attention module and a deep intra-group fusion module. In addition, a fast spatial alignment is proposed to handle videos with large motion. Extensive results demonstrate the capability of the proposed model in handling videos with various motion. It achieves favorable performance against state-of-the-art methods on several benchmark datasets.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results2017
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Learning Features by Watching Objects Move2017
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Video Super-Resolution With Convolutional Neural NetworksIEEE Transactions on Computational Imaging, 2016
- Video Super-Resolution via Deep Draft-Ensemble Learning2015
- On Bayesian Adaptive Video Super ResolutionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004