arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.04127cs.CVcs.GR
收藏

HumanNeRF:单目视频中运动人物的自由视点绘制

HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video

University of Washington(华盛顿大学);Google Research(谷歌研究院)

Chung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron, Ira Kemelmacher-Shlizerman

摘要:

我们介绍了一种自由视点渲染方法- HumanNeRF -它适用于一个给定的单目视频的人执行复杂的身体运动,例如,从YouTube的视频。我们的方法可以在任何帧暂停视频,并从任意新的摄像机视点或甚至针对该特定帧和身体姿势的完整360度摄像机路径渲染主体。这项任务特别具有挑战性,因为它需要合成身体的照片般逼真的细节,如从输入视频中可能不存在的各种相机角度看到的,以及合成精细的细节,如衣服褶皱和面部外观。我们的方法优化了一个典型的T-姿势的人的体积表示,与运动场,通过向后扭曲映射估计的规范表示到视频的每一帧。运动场被分解为由深度网络产生的骨架刚性和非刚性运动。我们显示了显着的性能改进比以前的工作,和令人信服的例子,从单目视频的移动人类在具有挑战性的不受控制的捕捉场景的自由视点渲染。

英文摘要:

We introduce a free-viewpoint rendering method -- HumanNeRF -- that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 360-degree camera path for that particular frame and body pose. This task is particularly challenging, as it requires synthesizing photorealistic details of the body, as seen from various camera angles that may not exist in the input video, as well as synthesizing fine details such as cloth folds and facial appearance. Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via backward warps. The motion field is decomposed into skeletal rigid and non-rigid motions, produced by deep networks. We show significant performance improvements over prior work, and compelling examples of free-viewpoint renderings from monocular video of moving humans in challenging uncontrolled capture scenarios.

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。

↑