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 1602.02023cs.CVcs.GR
收藏

精细表面细节的高效多视图性能捕获

Efficient Multi-view Performance Capture of Fine-Scale Surface Detail

MPI Informatik(马克斯·普朗克信息学研究所);Intel VCI(英特尔视觉计算研究所);CEUNES / UFES(圣埃斯皮里图联邦大学北部高地高级研究中心);Pixargus / GoalControl(Pixargus/GoalControl公司)

Nadia Robertini, Edilson De Aguiar, Thomas Helten, Christian Theobalt

摘要:

提出了一种新的有效方法,用于从多视点视频中捕获具有精细尺度时变表面细节的变形网格。我们的方法建立在粗糙的4D表面重建,获得常用的基于模板的方法。由于它们仅捕获粗到中等尺度细节的模型,因此细尺度变形细节通常通过使用立体约束、特征或基于阴影的细化在第二遍中完成。在本文中,我们提出了一个新的有效和稳定的解决方案,这第二步。我们的框架使用表面上的3D高斯函数的密集集合和图像的2D高斯函数集来创建可变形网格的隐式表示。通过在所有顶点位置上密集地优化新的模型到图像一致性能量,可以有效地找到使照片一致性最大化的所有网格顶点的精细尺度变形。一个主要的优点是,我们的问题制定产生一个光滑的封闭形式的能量与隐式遮挡处理和解析导数。也不需要容易出错的对应查找或表面位移值的离散采样。我们展示了几个穿着宽松衣服的人类受试者的重建,我们定性和定量地表明,我们鲁棒地捕捉更多的细节比相关的方法。

英文摘要:

We present a new effective way for performance capture of deforming meshes with fine-scale time-varying surface detail from multi-view video. Our method builds up on coarse 4D surface reconstructions, as obtained with commonly used template-based methods. As they only capture models of coarse-to-medium scale detail, fine scale deformation detail is often done in a second pass by using stereo constraints, features, or shading-based refinement. In this paper, we propose a new effective and stable solution to this second step. Our framework creates an implicit representation of the deformable mesh using a dense collection of 3D Gaussian functions on the surface, and a set of 2D Gaussians for the images. The fine scale deformation of all mesh vertices that maximizes photo-consistency can be efficiently found by densely optimizing a new model-to-image consistency energy on all vertex positions. A principal advantage is that our problem formulation yields a smooth closed form energy with implicit occlusion handling and analytic derivatives. Error-prone correspondence finding, or discrete sampling of surface displacement values are also not needed. We show several reconstructions of human subjects wearing loose clothing, and we qualitatively and quantitatively show that we robustly capture more detail than related 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。

↑