Smooth Loops from Unconstrained Video
Smooth Loops from Unconstrained Video
复制标题
无约束视频的平滑循环
DOI：
10.1111/cgf.12682
复制
发表时间：
2015
影响因子：
2.5
通讯作者：
Eli Shechtman
中科院分区：
文献类型：
--
作者：
Laura Sevilla;Jonas Wulff;Kalyan Sunkavalli;Eli Shechtman
将不受约束的视频序列转换为无缝循环的视频是一个极具挑战性的问题。在这项工作中，我们通过专注于包含单个主要前景对象的重要视频子类，迈出了自动化此过程的第一步。我们的技术在之前的工作中做出了两个新颖的贡献：首先，我们提出了一个基于对应的相似性度量来自动识别视频中前景的外观和动态最一致的良好过渡点。其次，我们开发了一种技术，该技术使用全局摄像机路径规划和基于补丁的视频变形相结合，对该过渡点的前景和背景进行对齐。我们证明，这使我们能够从互联网上收集的各种视频中创建自然，引人注目，循环的视频。
Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence‐based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch‐based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.