arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.10434cs.CVcs.GR
收藏

基于动态模板构造的三维人体运动鲁棒重建

Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

University of Delaware(特拉华大学);Plex-VR;Louisiana State University(路易斯安那州立大学);ShanghaiTech University(上海科技大学)

Zhong Li, Yu Ji, Wei Yang, Jinwei Ye, Jingyi Yu

摘要:

在多视图人体捕获系统中,由于遮挡、噪声、有限的视场等,恢复的3D几何形状甚至所获取的图像数据可能严重损坏。在这些低质量数据上直接估计3D姿态、身体形状或运动传统上具有挑战性。我们提出了一个基于图的非刚性形状配准框架,可以同时恢复3D人体几何形状和估计姿态/运动在高保真度。我们的方法首先生成一个全局的完整的,首先通过配准运动序列中的所有姿态,构造出人体模板,然后利用模板中的刚体成分构造出可变形图。我们直接将全局模板图扭曲回每个运动帧,以填充丢失的几何图形。具体来说,我们结合局部刚性和时间相干性约束,以保持几何和运动的连续性。各种场景的综合实验表明,我们的方法是准确的和强大的,即使在激烈的运动。

英文摘要:

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc. Direct estimation of 3D pose, body shape or motion on these low-quality data has been traditionally challenging.In this paper, we present a graph-based non-rigid shape registration framework that can simultaneously recover 3D human body geometry and estimate pose/motion at high fidelity.Our approach first generates a global full-body template by registering all poses in the acquired motion sequence.We then construct a deformable graph by utilizing the rigid components in the global template. We directly warp the global template graph back to each motion frame in order to fill in missing geometry. Specifically, we combine local rigidity and temporal coherence constraints to maintain geometry and motion consistencies. Comprehensive experiments on various scenes show that our method is accurate and robust even in the presence of drastic motions.

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。

↑