6-DoF Object Pose from Semantic Keypoints
Not on the map. Why?
Abstract (arXiv)
This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior work, we are agnostic to whether the object is textured or textureless, as the convnet learns the optimal representation from the available training image data. Furthermore, the approach can be applied to instance- and class-based pose recovery. Empirically, we show that the proposed approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios with a cluttered background. For class-based object pose estimation, state-of-the-art accuracy is shown on the large-scale PASCAL3D+ dataset.
Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Mar 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 29; 2022: 25; 2023: 13; 2024: 8; 2025: 9; 2026: 5.
89 papers.
Sort:
By area:
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
- 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
- 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
- 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
- 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
- 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
- 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
- 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
- 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
- 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
- 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42
38 more
- 2021NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimationcited by 41
- 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
- 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
- 2021Single-view robot pose and joint angle estimation via render & comparecited by 33
- 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
- 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 32
- 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
- 2021VS-Net: Voting with Segmentation for Visual Localizationcited by 29
- 2021Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Votingcited by 25
- 2022Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Featurescited by 23
- 2022Neural Correspondence Field for Object Pose Estimationcited by 21
- 2022Focal Length and Object Pose Estimation via Render and Comparecited by 17
- 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
- 2021Optimal Pose and Shape Estimation for Category-level 3D Object Perceptioncited by 15
- 2021MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentationcited by 15
- 2021Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Posecited by 15
- 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
- 2021PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimationcited by 14
- 2022PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimationcited by 13
- 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
- 2023Diff-DOPE: Differentiable Deep Object Pose Estimationcited by 11
- 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 10
- 2021KDFNet: Learning Keypoint Distance Field for 6D Object Pose Estimationcited by 9
- 2022MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Networkcited by 9
- 2024CRISP: Object Pose and Shape Estimation with Test-Time Adaptationcited by 9
- 2022Semantic keypoint-based pose estimation from single RGB framescited by 7
- 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimationcited by 7
- 2024Reconstructing Animals and the Wildcited by 7
- 2021Fully Convolutional Geometric Features for Category-level Object Alignmentcited by 6
- 2021Occlusion-Robust Object Pose Estimation with Holistic Representationcited by 6
- 2022Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypointscited by 6
- 2023A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Trainingcited by 6
- 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6
- 2021VIPose: Real-time Visual-Inertial 6D Object Pose Trackingcited by 5
- 2022Video based Object 6D Pose Estimation using Transformerscited by 5
- 2021Localization and Mapping using Instance-specific Mesh Modelscited by 4
- 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesiscited by 4
- 2026Picasso: Holistic Scene Reconstruction with Physics-Constrained Samplingcited by 4
50 most cited of 89 All 89 (JSON)
- 2026Detecting Pose Estimation Failures via Keypoint Self-Consistency4 Aug 2026
- 2026ComPose: When to Trust Hands for Object Pose Tracking22 May 2026
- 2026HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labeling23 Mar 2026
- 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation20 Mar 2026
- 2026Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling8 Feb 2026
- 2025PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects28 Dec 2025
- 2025DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects13 Oct 2025
- 2025PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation8 Aug 2025
- 2025Box Pose and Shape Estimation and Domain Adaptation for Large-Scale Warehouse Automation1 Jul 2025
- 2025Deterministic Object Pose Confidence Region Estimation28 Jun 2025
- 2025DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates9 Apr 2025
- 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames5 Mar 2025
38 more
- 2025Monocular Person Localization under Camera Ego-motion4 Mar 2025
- 2025Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection17 Feb 2025
- 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting2 Dec 2024
- 2024CRISP: Object Pose and Shape Estimation with Test-Time Adaptation2 Dec 2024
- 2024Reconstructing Animals and the Wild27 Nov 2024
- 2024ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depth23 Aug 2024
- 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Survey13 May 2024
- 2024GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation8 May 2024
- 2024Learning a Category-level Object Pose Estimator without Pose Annotations8 Apr 2024
- 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation19 Jan 2024
- 2023FoundPose: Unseen Object Pose Estimation with Foundation Features30 Nov 2023
- 2023FocalPose++: Focal Length and Object Pose Estimation via Render and Compare15 Nov 2023
- 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation26 Oct 2023
- 2023Diff-DOPE: Differentiable Deep Object Pose Estimation30 Sep 2023
- 2023Learning Better Keypoints for Multi-Object 6DoF Pose Estimation15 Aug 2023
- 2023YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation21 Jul 2023
- 2023TransPose: A Transformer-based 6D Object Pose Estimation Network with Depth Refinement9 Jul 2023
- 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis31 May 2023
- 2023Robust Category-Level 3D Pose Estimation from Synthetic Data25 May 2023
- 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network29 Mar 2023
- 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation22 Mar 2023
- 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation21 Mar 2023
- 2023A Correct-and-Certify Approach to Self-Supervise Object Pose Estimators via Ensemble Self-Training12 Feb 2023
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare13 Dec 2022
- 2022Context-aware 6D Pose Estimation of Known Objects using RGB-D data11 Dec 2022
- 2022Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding4 Dec 2022
- 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation1 Dec 2022
- 2022PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation25 Nov 2022
- 2022Video based Object 6D Pose Estimation using Transformers24 Oct 2022
- 2022Real-time Detection of 2D Tool Landmarks with Synthetic Training Data21 Oct 2022
- 2022Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences28 Sep 2022
- 2022CPnP: Consistent Pose Estimator for Perspective-n-Point Problem with Bias Elimination13 Sep 2022
- 2022Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features12 Sep 2022
- 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation3 Aug 2022
- 2022MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network1 Aug 2022
- 2022Neural Correspondence Field for Object Pose Estimation30 Jul 2022
- 2022Instance-specific 6-DoF Object Pose Estimation from Minimal Annotations27 Jul 2022
- 2022Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints24 Jun 2022
50 newest of 89 All 89 (JSON)
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
- 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
- 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
- 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
- 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
- 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
- 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
- 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
- 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
- 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
- 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42
12 most cited of 87 All 87 (JSON)
- 2026Detecting Pose Estimation Failures via Keypoint Self-Consistency4 Aug 2026
- 2026ComPose: When to Trust Hands for Object Pose Tracking22 May 2026
- 2026HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labeling23 Mar 2026
- 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation20 Mar 2026
- 2026Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling8 Feb 2026
- 2025PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects28 Dec 2025
- 2025DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects13 Oct 2025
- 2025PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation8 Aug 2025
- 2025Box Pose and Shape Estimation and Domain Adaptation for Large-Scale Warehouse Automation1 Jul 2025
- 2025Deterministic Object Pose Confidence Region Estimation28 Jun 2025
- 2025DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates9 Apr 2025
- 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames5 Mar 2025
12 newest of 87 All 87 (JSON)