HybridPose: 6D Object Pose Estimation under Hybrid Representations

Chen Song, Jiaru Song, Qixing Huang
1/7/2020
cs.CV

Official code: chensong1995/HybridPose (434 stars, MIT, last commit 2024-07-15).

Abstract

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). Different intermediate representations used by HybridPose can all be predicted by the same simple neural network, and outliers in predicted intermediate representations are filtered by a robust regression module. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and accuracy. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 47.5%, representing a state-of-the-art performance. The implementation of HybridPose is available at https://github.com/chensong1995/HybridPose.

View on arXivView PDF

Code Implementations(1)

chensong1995/HybridPoseOfficial100%
MIT

HybridPose: 6D Object Pose Estimation under Hybrid Representation (CVPR 2020)

43460C, C++Dec 11, 20192 years agoMIT

Similar Papers

GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation

87% match2025

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

86% match1 repo332018

GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation

86% match1 repo152025

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

85% match1 repo4562024

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

85% match1 repo482024

Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation

85% match2024

Cite this paper

@article{song2020hybridpose,
  title  = {HybridPose: 6D Object Pose Estimation under Hybrid Representations},
  author = {Chen Song and Jiaru Song and Qixing Huang},
  year   = {2020},
  eprint = {2001.01869},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2001.01869}
}

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/2001.01869.svg)](https://codeofpaper.com/paper/2001.01869)

Discussion