Frame Selection Using Spatiotemporal Dynamics and Key Features as Input Pre-processing for Video Super-Resolution Models

Author:

Agrahari Baniya ArbindORCID,Lee Tsz-KwanORCID,Eklund PeterORCID,Aryal SunilORCID

Abstract

AbstractThis paper presents a novel approach to video super-resolution (VSR) by focusing on the selection of input frames, a process critical to VSR. VSR methods typically rely on deep learning techniques, those that are able to learn features from a large dataset of low-resolution (LR) and corresponding high-resolution (HR) videos and generate high-quality HR frames from any new LR input frames using the learned features. However, these methods often use as input the immediate neighbouring frames to a given target frame without considering the importance and dynamics of the frames across the temporal dimension of a video. This work aims to address the limitations of the conventional sliding-window mechanisms by developing input frame selection algorithms. By dynamically selecting the most representative neighbouring frames based on content-aware selection measures, our proposed algorithms enable VSR models to extract more informative and accurate features that are better aligned with the target frame, leading to improved performance and higher-quality HR frames. Through an empirical study, we demonstrate that the proposed dynamic content-aware selection mechanism improves super-resolution results without any additional architectural overhead, offering a counter-intuitive yet effective alternative to the long-established trend of increasing architectural complexity to improve VSR results.

Funder

Deakin University

Publisher

Springer Science and Business Media LLC

Reference44 articles.

1. Wang Z, Chen J, Hoi SC. Deep learning for image super-resolution: A survey. IEEE transactions on pattern analysis and machine intelligence; 2020.

2. Arefin MR, Michalski V, St-Charles P-L, Kalaitzis A, Kim S, Kahou SE, Bengio Y. Multi-image super-resolution for remote sensing using deep recurrent networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020;pp. 206–207.

3. Liang M, Du J, Li L, Xue Z, Wang X, Kou F, Wang X. Video super-resolution reconstruction based on deep learning and spatio-temporal feature self-similarity. IEEE Transactions on Knowledge and Data Engineering. 2020;1–1. https://doi.org/10.1109/TKDE.2020.3034261.

4. Liu Z-S, Siu W-C, Chan Y-L. Efficient video super-resolution via hierarchical temporal residual networks. IEEE Access. 2021;9:106049–64. https://doi.org/10.1109/ACCESS.2021.3098326.

5. Liu H, Ruan Z, Zhao P, Dong C, Shang F, Liu Y, Yang L. Video super resolution based on deep learning: A comprehensive survey. arXiv preprint arXiv:2007.12928 2020.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A Survey of Deep Learning Video Super-Resolution;IEEE Transactions on Emerging Topics in Computational Intelligence;2024-08

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3