arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.12928cs.CVeess.IV
收藏

基于深度学习的视频超分辨率研究综述

Video Super Resolution Based on Deep Learning: A Comprehensive Survey

Xidian University(西安电子科技大学);Peng Cheng Laboratory(鹏城实验室);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);ETH Zurich(苏黎世联邦理工学院);University of Wurzburg(维尔茨堡大学)

Hongying Liu, Zhubo Ruan, Peng Zhao, Chao Dong, Fanhua Shang, Yuanyuan Liu, Linlin Yang, Radu Timofte

摘要:

近年来,深度学习在图像识别、自然语言处理、语音识别、视频超分辨率等多个领域取得了长足的进展。在本次调查中,我们全面调查了33种基于深度学习的最先进的视频超分辨率(VSR)方法。众所周知,视频帧内的信息的利用对于视频超分辨率是重要的。因此,我们提出了一种分类法,并根据利用帧间信息的方式将这些方法分为六个子类。此外,所有的方法的体系结构和实现细节进行了详细描述。最后,我们总结并比较了代表性的VSR方法在一些基准数据集上的性能。我们还讨论了一些挑战,需要进一步解决的研究人员在社区的VSR。据我们所知,这项工作是第一个系统的VSR任务,它有望在这一领域的最新研究的发展作出贡献,并可能加深我们对基于深度学习的VSR技术的理解。

英文摘要:

In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning. It is well known that the leverage of information within video frames is important for video super-resolution. Thus we propose a taxonomy and classify the methods into six sub-categories according to the ways of utilizing inter-frame information. Moreover, the architectures and implementation details of all the methods are depicted in detail. Finally, we summarize and compare the performance of the representative VSR method on some benchmark datasets. We also discuss some challenges, which need to be further addressed by researchers in the community of VSR. To the best of our knowledge, this work is the first systematic review on VSR tasks, and it is expected to make a contribution to the development of recent studies in this area and potentially deepen our understanding to the VSR techniques based on deep learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑