开源算法
【MIT & Princeton 做的物体抓取算法】
基本思想:基于深度学习物体语义分割 -> 基于事先建好的模型进行ICP匹配获得位姿
特色:利用自监督学习减少数据的依赖性
【TECHNISCHE UNIVERSITAT DRESDEN】
【ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes】
【RSS 2018 & code】 PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
【2018MIT的成果,对应伯克利的Dexnet2.0】 Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulat
【ICRA 2018】Improving 6D Pose Estimation of Objects in Clutter via Physics-aware Monte Carlo Tree Search
概述:基本思路是CNN图像分割+CAD模型匹配,论文主要在CAD模型匹配时提出了Monte Carlo树搜索提升效果
【Paper】End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans, Technical University of Munich
【 仅需3D模型的高效视觉系统机器手控制】 CRAVES: Controlling Robotic Arm with a Vision-based, Economic System
【CVPR 2019】Segmentation-driven 6D Ob