Saved in:
Bibliographic Details
Main Authors: Wang, Hai, Xiang, Xiaoyu, Tian, Yapeng, Yang, Wenming, Liao, Qingmin
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2203.06841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915489446363136
author Wang, Hai
Xiang, Xiaoyu
Tian, Yapeng
Yang, Wenming
Liao, Qingmin
author_facet Wang, Hai
Xiang, Xiaoyu
Tian, Yapeng
Yang, Wenming
Liao, Qingmin
contents The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this paper, we propose a deformable attention network called STDAN for STVSR. First, we devise a long-short term feature interpolation (LSTFI) module, which is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional RNN structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.
format Preprint
id arxiv_https___arxiv_org_abs_2203_06841
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle STDAN: Deformable Attention Network for Space-Time Video Super-Resolution
Wang, Hai
Xiang, Xiaoyu
Tian, Yapeng
Yang, Wenming
Liao, Qingmin
Computer Vision and Pattern Recognition
The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this paper, we propose a deformable attention network called STDAN for STVSR. First, we devise a long-short term feature interpolation (LSTFI) module, which is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional RNN structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.
title STDAN: Deformable Attention Network for Space-Time Video Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2203.06841