Real-Time Object Pose Estimation with Pose Interpreter Networks

Jimmy Wu, Bolei Zhou, Rebecca Russell, Vincent Kee, Syler Wagner +3 more
8/3/2018
cs.ROcs.CV

Official code: jimmyyhwu/pose-interpreter-networks (126 stars, MIT, PyTorch, last commit 2023-04-11).

Abstract

In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our end-to-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement.

View on arXivView PDF

Code Implementations(1)

jimmyyhwu/pose-interpreter-networksOfficial100%
PyTorchMIT

Real-time robotic object pose estimation with deep learning

12628CMake, ShellJul 4, 20183 years agoMIT
3dartificial-intelligencecomputer-visiondeep-learningobject-pose-estimation+3 more

Similar Papers

Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

88% match1 repo402023

NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models

87% match1 repo102024

Vision Foundation Model Enables Generalizable Object Pose Estimation

86% match2024

SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation

86% match1 repo22023

One2Any: One-Reference 6D Pose Estimation for Any Object

86% match2025

GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence

86% match2023

Cite this paper

@article{wu2018realtime,
  title  = {Real-Time Object Pose Estimation with Pose Interpreter Networks},
  author = {Jimmy Wu and Bolei Zhou and Rebecca Russell and Vincent Kee and Syler Wagner and Mitchell Hebert and Antonio Torralba and David M. S. Johnson},
  year   = {2018},
  eprint = {1808.01099},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1808.01099}
}

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/1808.01099.svg)](https://codeofpaper.com/paper/1808.01099)

Discussion