Robust 6D Object Pose Estimation by Learning RGB-D Features

02/29/2020
by   Meng Tian, et al.
0

Accurate 6D object pose estimation is fundamental to robotic manipulation and grasping. Previous methods follow a local optimization approach which minimizes the distance between closest point pairs to handle the rotation ambiguity of symmetric objects. In this work, we propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Additionally, the object location is detected by aggregating point-wise vectors pointing to the 3D center. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches. Our code is available at https://github.com/mentian/object-posenet.

READ FULL TEXT

page 1

page 3

page 6

research
11/25/2022

PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation

Accurate 6D object pose estimation is an important task for a variety of...
research
08/03/2022

SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation

This paper presents an efficient symmetry-agnostic and correspondence-fr...
research
09/26/2019

Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints

Planar markers are useful in robotics and computer vision for mapping an...
research
02/27/2023

Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction

Predicting the pose of objects from a single image is an important but d...
research
11/02/2022

Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulation

6D object pose estimation aims to infer the relative pose between the ob...
research
02/25/2022

6D Rotation Representation For Unconstrained Head Pose Estimation

In this paper, we present a method for unconstrained end-to-end head pos...
research
08/12/2020

PAM:Point-wise Attention Module for 6D Object Pose Estimation

6D pose estimation refers to object recognition and estimation of 3D rot...

Please sign up or login with your details

Forgot password? Click here to reset