6D Object Pose

6D object pose estimation aims to determine an object's three-dimensional position and orientation within a scene, a crucial task in robotics and computer vision. Current research heavily utilizes deep learning, particularly convolutional neural networks (CNNs) and transformers, often incorporating techniques like deep ensembles for uncertainty quantification and render-and-compare methods for improved accuracy, especially with challenging objects. These advancements are driving progress in applications such as robotic manipulation, augmented reality, and autonomous navigation, where precise and robust pose estimation is essential for safe and efficient operation. Furthermore, research is actively exploring open-vocabulary pose estimation and handling of dynamic objects, expanding the capabilities and applicability of this technology.

Papers

June 13, 2024

Deep Transformer Network for Monocular Pose Estimation of Ship-Based UAV
Maneesha Wickramasuriya, Taeyoung Lee, Murray Snyder
Unmanned Aerial Vehicle Deep Transformer 6D Object Pose Transformer Neural Ship Landing

March 12, 2024

Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
Kira Wursthorn, Markus Hillemann, Markus Ulrich
Uncertainty Quantification Deep Ensemble 6D Object 6D Object Pose Estimation Pose Estimate 6D Object Pose Deep Uncertainty

December 1, 2023

Open-vocabulary object 6D pose estimation
Jaime Corsetti, Davide Boscaini, Changjae Oh, Andrea Cavallaro, Fabio Poiesi
Vision Language Model Estimation Task Object Level 6D Object Pose

November 9, 2023

Visually Guided Model Predictive Robot Control via 6D Object Pose Localization and Tracking
Mederic Fourmy, Vojtech Priban, Jan Kristof Behrens, Nicolas Mansard, Josef Sivic, Vladimir Petrik
Web Tracking 6D Object Nonlinear Model Predictive Control 6D Object Pose Estimation Pose Control Pose Tracking 6D Object Pose

October 24, 2022

Video based Object 6D Pose Estimation using Transformers
Apoorva Beedu, Huda Alamri, Irfan Essa
Transformer Megatron Decepticons Source Video Video Dataset 6D Object Pose Estimation Pose Refinement 6D Object Pose

October 11, 2022

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Hongyang Li, Jiehong Lin, Kui Jia
Human Pose 6D Object 6D Pose Estimation 6D Object Pose DCL Net

September 16, 2022

Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Jiri Sedlar, Karla Stepanova, Radoslav Skoviera, Jan K. Behrens, Matus Tuna, Gabriela Sejnova, Josef Sivic, Robert Babuska
Training Data Imitation Learning 6D Object 6D Object Pose Estimation 6D Object Pose

August 21, 2022

CenDerNet: Center and Curvature Representations for Render-and-Compare 6D Pose Estimation
Peter De Roovere, Rembert Daems, Jonathan Croenen, Taoufik Bourgana, Joris de Hoog, Francis Wyffels
Multi View Image Stable Pose ATAC Net 6D Pose Estimation 3D Point 6D Object Pose Center Voting Curvature Space

May 23, 2022

ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Poses
Arul Selvam Periyasamy, Catherine Capellen, Max Schwarz, Sven Behnke
Human Prediction Video Dataset Fully Convolutional Pose Network 6D Object Pose Orientation Prediction

April 20, 2022

HRPose: Real-Time High-Resolution 6D Pose Estimation Network Using Knowledge Distillation
Qi Guan, Zihao Sheng, Shibei Xue
Knowledge Distillation Robotic Grasping 6D Object Pose Estimation Network 6D Object Pose

April 4, 2022

Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image
Zhaoxin Fan, Zhenbo Song, Jian Xu, Zhicheng Wang, Kejian Wu, Hongyan Liu, Jun He
6D Object RGB Image Category Level 6D Object Pose 6D Object Pose Object Depth

March 7, 2022

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild
Yang You, Ruoxi Shi, Weiming Wang, Cewu Lu
Wild Challenge Category Level Robust Pose Estimation Category Level 6D Object Pose Point Pair 6D Object Pose

December 9, 2021

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann
Strategic Manipulation Object Representation Local Descriptor 6D Object Pose Category Specific

November 6, 2021

ROFT: Real-Time Optical Flow-Aided 6D Object Pose and Velocity Tracking
Nicola A. Piga, Yuriy Onyshchuk, Giulia Pasquale, Ugo Pattacini, Lorenzo Natale
Optical Flow 6D Object Pose Estimation Velocity Estimation 6D Object Pose 6 DoF Tracking