Category-Level Articulated Object Pose Estimation
Category-Level Articulated Object Pose Estimation
复制标题
DOI：
10.1109/cvpr42600.2020.00376
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Xiaolong Li;He Wang;L. Yi;L. Guibas;A. L. Abbott;Shuran Song
中科院分区：
文献类型：
--
作者：
Xiaolong Li;He Wang;L. Yi;L. Guibas;A. L. Abbott;Shuran Song
本文讨论了从单个深度图像中对关节式物体进行类别级姿态估计的任务。我们提出了一种新的类别级方法，可以正确地容纳以前在训练过程中看不到的对象实例。我们介绍了关节感知规范化坐标空间层次结构（ANCSH）-一个规范的表示在给定的类别中不同的关节对象。作为实现类内泛化的关键，该表示构造了一个规范的对象空间和一组规范的部分空间。规范对象空间规范化对象取向、尺度和关节（例如，关节参数和状态），而每个规范部件空间进一步规范化其部件姿态和尺度。我们开发了一个基于PointNet++的深度网络，它可以从单个深度点云预测ANCSH，包括规范对象空间中的部分分割、归一化坐标和关节参数。通过利用规范化的关节，我们证明：1）使用来自关节的诱导运动学约束改进了部分姿态和尺度估计的性能; 2）相机空间中关节参数估计的高精度。
This paper addresses the task of category-level pose estimation for articulated objects from a single depth image. We present a novel category-level approach that correctly accommodates object instances previously unseen during training. We introduce Articulation-aware Normalized Coordinate Space Hierarchy (ANCSH) – a canonical representation for different articulated objects in a given category. As the key to achieve intra-category generalization, the representation constructs a canonical object space as well as a set of canonical part spaces. The canonical object space normalizes the object orientation, scales and articulations (e.g. joint parameters and states) while each canonical part space further normalizes its part pose and scale. We develop a deep network based on PointNet++ that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space. By leveraging the canonicalized joints, we demonstrate: 1) improved performance in part pose and scale estimations using the induced kinematic constraints from joints; 2) high accuracy for joint parameter estimation in camera space.