PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

Yisheng He, Wei Sun, Haibin Huang, Jianran Liu, Haoqiang Fan +1 more
11/11/2019
cs.CVcs.RO

Official code: ethnhe/PVN3D (541 stars, MIT, last commit 2022-12-27).

Abstract

In this work, we present a novel data-driven method for robust 6DoF object pose estimation from a single RGBD image. Unlike previous methods that directly regressing pose parameters, we tackle this challenging task with a keypoint-based approach. Specifically, we propose a deep Hough voting network to detect 3D keypoints of objects and then estimate the 6D pose parameters within a least-squares fitting manner. Our method is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation. It allows us to fully utilize the geometric constraint of rigid objects with the extra depth information and is easy for a network to learn and optimize. Extensive experiments were conducted to demonstrate the effectiveness of 3D-keypoint detection in the 6D pose estimation task. Experimental results also show our method outperforms the state-of-the-art methods by large margins on several benchmarks. Code and video are available at https://github.com/ethnhe/PVN3D.git.

View on arXivView PDF

Code Implementations(1)

ethnhe/PVN3DOfficial100%
MIT

Code for "PVN3D: A Deep Point-wise 3D Keypoints Hough Voting Network for 6DoF Pose Estimation", CVPR 2020

541106C, C++Sep 16, 20193 years agoMIT

Similar Papers

Estimating 6D Pose From Localizing Designated Surface Keypoints

89% match1 repo702018

Segmentation-driven 6D Object Pose Estimation

88% match1 repo2002018

Object Pose Estimation from Monocular Image using Multi-View Keypoint Correspondence

87% match1 repo332018

DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates

87% match2025

A Graph-Based Approach for Category-Agnostic Pose Estimation

87% match1 repo3892023

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation

87% match1 repo122023

Cite this paper

@article{he2019pvnd,
  title  = {PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation},
  author = {Yisheng He and Wei Sun and Haibin Huang and Jianran Liu and Haoqiang Fan and Jian Sun},
  year   = {2019},
  eprint = {1911.04231},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.04231}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.04231.svg)](https://codeofpaper.com/paper/1911.04231)

Discussion