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 1905.04789cs.CV
收藏

Structure from Articulated Motion:无训练数据的单目3D重建

Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data

German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);University of Kaiserslautern(凯泽斯劳滕大学);University of Prince Mugrin (UPM)(穆格林王子大学)

Onorina Kovalenko, Vladislav Golyanik, Jameel Malik, Ahmed Elhayek, Didier Stricker

摘要:

从二维观测数据中恢复关节式三维结构是一个具有挑战性的计算机视觉问题。目前基于学习的方法在公共基准上达到了最先进的精度,但仅限于训练数据集所涵盖的特定类型的对象和运动。基于模型的方法不依赖于训练数据,但在这些数据集上显示出较低的准确性。在本文中,我们介绍了一种基于模型的方法,称为结构从关节运动(SfAM),它可以恢复多个对象和运动类型,而无需训练广泛的数据汇集。同时,它在公共基准测试中的表现与基于学习的最先进方法不相上下,并且优于以前的非刚性运动恢复结构(NRSfM)方法。SfAM建立在通用NRSfM技术的基础上,同时集成了对骨长度的软时空约束。我们使用交替优化策略来恢复最佳几何形状(即,骨骼比例)以及3D关节位置。SfAM对噪声2D注释具有高度鲁棒性,可推广到任意对象,并且不依赖于训练数据,这在公共基准测试和真实视频序列上的大量实验中显示。我们相信,它带来了一个新的视角上的单目3D恢复关节结构,包括人体运动捕捉的域。

英文摘要:

Recovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are restricted to specific types of objects and motions covered by the training datasets. Model-based approaches do not rely on training data but show lower accuracy on these datasets. In this paper, we introduce a model-based method called Structure from Articulated Motion (SfAM), which can recover multiple object and motion types without training on extensive data collections. At the same time, it performs on par with learning-based state-of-the-art approaches on public benchmarks and outperforms previous non-rigid structure from motion (NRSfM) methods. SfAM is built upon a general-purpose NRSfM technique while integrating a soft spatio-temporal constraint on the bone lengths. We use alternating optimization strategy to recover optimal geometry (i.e., bone proportions) together with 3D joint positions by enforcing the bone lengths consistency over a series of frames. SfAM is highly robust to noisy 2D annotations, generalizes to arbitrary objects and does not rely on training data, which is shown in extensive experiments on public benchmarks and real video sequences. We believe that it brings a new perspective on the domain of monocular 3D recovery of articulated structures, including human motion capture.

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。

↑