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.
翻译:近年来,在图像识别、自然语言处理、语音识别和视频超分辨率等许多领域,深层学习取得了巨大进展。在本次调查中,我们全面调查了33种基于深层学习的最新视频超分辨率方法。众所周知,视频框架内信息的杠杆作用对于视频超分辨率非常重要。因此,我们建议进行分类,并按照利用跨框架信息的方式将方法分为6个亚类。此外,还详细描述了所有方法的结构和实施细节。最后,我们总结并比较了具有代表性的 VSR 方法在某些基准数据集上的绩效。我们还讨论了一些挑战,需要由VSR 社区的研究人员进一步应对。根据我们的知识,这项工作是对VSR 任务的首次系统审查,预计将对该领域近期研究的发展作出贡献,并有可能加深我们对基于深层学习的VSR 技术的理解。