arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.08809cs.CV
收藏

学习隐式表示以重建关节物体

Learning Implicit Representation for Reconstructing Articulated Objects

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja

AI总结:

本文提出一种无需类别特定骨架的关节物体重建方法,通过从视频运动线索中同时学习显式三维表示和由骨架、蒙皮权重、刚性系数及时变变换构成的隐式表示,并在标准数据集上取得优于现有方法的性能。

摘要:

在没有关于物体结构的额外信息的情况下,对运动中的关节物体进行三维重建是一个具有挑战性的问题。当前方法通过采用类别特定的骨骼模型来克服此类挑战,因此它们对自然场景中的关节物体泛化能力较差。我们将关节物体视为一个未知的半刚性骨骼结构,其周围被非刚性材料(例如皮肤)包裹。我们的方法在没有三维监督的情况下,从物体视频中的运动线索同时估计可见的(显式)表示(三维形状、颜色、相机参数)和隐式骨骼表示。我们的隐式表示由四个部分组成。(1)骨架,指定半刚性部件如何连接。(2)蒙皮权重,以概率方式将每个表面顶点与半刚性部件关联起来。(3)刚性系数,指定局部表面的关节运动特性。(4)时变变换,指定骨骼运动和表面变形参数。我们引入了一种算法,该算法使用物理约束作为正则化项,并迭代地估计隐式和显式表示。我们的方法与类别无关,因此无需类别特定的骨架。我们表明,我们的方法在标准视频数据集上优于最先进的方法。

英文摘要:

3D Reconstruction of moving articulated objects without additional information about object structure is a challenging problem. Current methods overcome such challenges by employing category-specific skeletal models. Consequently, they do not generalize well to articulated objects in the wild. We treat an articulated object as an unknown, semi-rigid skeletal structure surrounded by nonrigid material (e.g., skin). Our method simultaneously estimates the visible (explicit) representation (3D shapes, colors, camera parameters) and the implicit skeletal representation, from motion cues in the object video without 3D supervision. Our implicit representation consists of four parts. (1) Skeleton, which specifies how semi-rigid parts are connected. (2) \textcolor{black}{Skinning Weights}, which associates each surface vertex with semi-rigid parts with probability. (3) Rigidity Coefficients, specifying the articulation of the local surface. (4) Time-Varying Transformations, which specify the skeletal motion and surface deformation parameters. We introduce an algorithm that uses physical constraints as regularization terms and iteratively estimates both implicit and explicit representations. Our method is category-agnostic, thus eliminating the need for category-specific skeletons, we show that our method outperforms state-of-the-art across standard video datasets.

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。

↑