arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07931cs.CV
收藏

从互联网视频中捕捉动作

Motion Capture from Internet Videos

State Key Lab of CAD&CG, Zhejiang University(浙江大学计算机辅助设计与图形学国家重点实验室);Zhejiang Lab(之江实验室)

Junting Dong, Qing Shuai, Yuanqing Zhang, Xian Liu, Xiaowei Zhou, Hujun Bao

摘要:

基于图像的人体姿态估计的最新进展使得从单个RGB视频捕获3D人体运动成为可能。然而,在一个单一的视图中固有的深度模糊性和自遮挡禁止恢复高质量的运动作为多视图重建。虽然多视图视频并不常见,但名人执行特定动作的视频通常在互联网上丰富。即使这些视频是在不同的时间记录的,它们也会对人的相同运动特征进行编码。因此,我们建议通过联合分析这些互联网视频来捕获人体运动,而不是单独使用单个视频。然而,这项新任务提出了许多现有方法无法解决的新挑战,因为视频是不同步的,摄像机视点是未知的,背景场景是不同的,并且视频之间的人体运动并不完全相同。为了解决这些挑战,我们提出了一种新的基于优化的框架,并通过实验证明了它能够从多个视频中恢复更精确和详细的运动,与单目运动捕捉方法相比。

英文摘要:

Recent advances in image-based human pose estimation make it possible to capture 3D human motion from a single RGB video. However, the inherent depth ambiguity and self-occlusion in a single view prohibit the recovery of as high-quality motion as multi-view reconstruction. While multi-view videos are not common, the videos of a celebrity performing a specific action are usually abundant on the Internet. Even if these videos were recorded at different time instances, they would encode the same motion characteristics of the person. Therefore, we propose to capture human motion by jointly analyzing these Internet videos instead of using single videos separately. However, this new task poses many new challenges that cannot be addressed by existing methods, as the videos are unsynchronized, the camera viewpoints are unknown, the background scenes are different, and the human motions are not exactly the same among videos. To address these challenges, we propose a novel optimization-based framework and experimentally demonstrate its ability to recover much more precise and detailed motion from multiple videos, compared against monocular motion capture methods.

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。

↑