arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.17261cs.CVcs.GRcs.HCcs.LG
收藏

用于浏览、编辑和传输视频的视频专用自动编码器

Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos

Carnegie Mellon University(卡内基梅隆大学)

Kevin Wang, Deva Ramanan, Aayush Bansal

摘要:

我们研究视频特定的自动编码器,允许人类用户探索,编辑和有效地传输视频。先前的工作已经独立地研究了这些问题(和子问题),并提出了不同的公式。在这项工作中,我们训练一个简单的自动编码器(从头开始)的多帧特定的视频。我们注意到:(1)由视频专用自动编码器学习的潜在代码捕获该视频的空间和时间属性;以及(2)自动编码器可以将样本外输入投影到视频专用流形上。这两个属性允许我们使用一个学习的表示来探索,编辑和有效地传输视频。例如,对潜在代码的线性操作允许用户可视化视频的内容。将视频的潜码与流形投影相关联,使用户能够进行所需的编辑。内插潜码和流形投影允许稀疏低分辨率帧在网络上传输。

英文摘要:

We study video-specific autoencoders that allow a human user to explore, edit, and efficiently transmit videos. Prior work has independently looked at these problems (and sub-problems) and proposed different formulations. In this work, we train a simple autoencoder (from scratch) on multiple frames of a specific video. We observe: (1) latent codes learned by a video-specific autoencoder capture spatial and temporal properties of that video; and (2) autoencoders can project out-of-sample inputs onto the video-specific manifold. These two properties allow us to explore, edit, and efficiently transmit a video using one learned representation. For e.g., linear operations on latent codes allow users to visualize the contents of a video. Associating latent codes of a video and manifold projection enables users to make desired edits. Interpolating latent codes and manifold projection allows the transmission of sparse low-res frames over a network.

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。

↑