【点云论文速读】6D位姿估计

标题：MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion

作者：Kentaro Wada, Edgar Sucar, Stephen James

星球ID：wl_华科_点云处理_目标识别

欢迎各位加入免费知识星球，获取PDF论文，欢迎转发朋友圈分享快乐。

●论文摘要

机器人与其他智能设备需要根据自身搭载的视觉系统实现高效的目标级场景表达以进行接触、物理、遮挡等推理。已知的精确目标模型在未知结构的非参数化重建中起着十分重要的作用。我们提出了一种系统，该系统能够估计实时多视角场景中接触、遮挡已知目标的精确位姿。我们的方法能从单一的RGBD视角估计3D目标位姿，随着相机的移动，能够从多个视角累积位姿估计和非参数化的occupancy信息，并执行联合优化来对接触的多个接触目标进行一致非交叉的位姿估计。

我们在YCB-Video和Cluttered YCB-Video两个数据集中对所提出的方法的精度和鲁棒性进行了实验验证。我们展示了一个实施的机器人应用，机器人仅用其搭载的RGB-D信息就能够精确有序的抓取复杂堆叠的物体。

https://github.com/j96w/DenseFusion

●论文图集

●英文摘要

Robots and other smart devices need efficient objectbased scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside non-parametric reconstructions of unrecognized structures. We present a system which can estimate the accurate poses of multiple known objects in contact and occlusion from real-time, embodied multi-view vision. Our approach makes 3D object pose proposals from single RGBD views, accumulates pose estimates and non-parametric occupancy information from multiple views as the camera moves, and performs joint optimization to estimate consistent, non-intersecting poses for multiple objects in contact. We verify the accuracy and robustness of our approach experimentally on 2 object datasets: YCB-Video, and our own challenging Cluttered YCB-Video. We demonstrate a  real-time robotics application where a robot arm precisely and orderly disassembles complicated piles of objects, using only on-board RGB-D vision