Video Super-resolution with Temporal Group Attention
arXiv:2007.10595
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.
CVPR 2020
References in corpus (7)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Learning for Single Image Super-Resolution: A Brief Review
- An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks
- Residual Dense Network for Image Super-Resolution
- 3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks
- Spatio-Temporal Attention Models for Grounded Video Captioning