OnePose: One-Shot Object Pose Estimation without CAD Models
Not on the map. Why?
Abstract (arXiv)
We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, OnePose does not rely on CAD models and can handle objects in arbitrary categories without instance- or category-specific network training. OnePose draws the idea from visual localization and only requires a simple RGB video scan of the object to build a sparse SfM model of the object. Then, this model is registered to new query images with a generic feature matching network. To mitigate the slow runtime of existing visual localization methods, we propose a new graph attention network that directly matches 2D interest points in the query image with the 3D points in the SfM model, resulting in efficient and robust pose estimation. Combined with a feature-based pose tracker, OnePose is able to stably detect and track 6D poses of everyday household objects in real-time. We also collected a large-scale dataset that consists of 450 sequences of 150 objects.
Key facts. Cited by 156 papers in the map (data through 13 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 24 May 2022.
Builds on
27 of 48 references.
References · 27
- 2017Graph Attention Networkscited by 8,888
- 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,994
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,439
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,316
- 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 984
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 979
- 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 770
- 2017Focal Loss for Dense Object Detectioncited by 750
- 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 557
- 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 492
- 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
- 2020DISK: Learning local features with policy gradientcited by 310
15 more
- 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
- 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
- 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
- 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
- 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 159
- 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
- 2020Fast Transformers with Clustered Attentioncited by 123
- 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
- 20176-DoF Object Pose from Semantic Keypointscited by 89
- 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
- 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
- 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
- 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
- 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
- 2017Toward Geometric Deep SLAMcited by 38
Built on by
Citing papers per year: 2022: 10; 2023: 38; 2024: 35; 2025: 41; 2026: 32.
156 papers.
Sort:
By area:
- 2023LightGlue: Local Feature Matching at Light Speedcited by 588
- 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 415
- 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 313
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 200
- 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 146
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 124
- 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
- 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
- 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
- 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 91
- 20243DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generationcited by 71
- 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
38 more
- 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
- 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
- 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 48
- 2024Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Trackingcited by 48
- 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
- 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
- 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
- 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
- 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 34
- 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 34
- 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
- 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
- 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
- 2023NeRF-Loc: Visual Localization with Conditional Neural Radiance Fieldcited by 29
- 2023Open-vocabulary object 6D pose estimationcited by 29
- 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
- 2026Orient Anything V2: Unifying Orientation and Rotation Understandingcited by 23
- 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
- 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
- 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
- 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
- 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 17
- 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
- 2022PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Trackingcited by 15
- 2025Dense-SfM: Structure from Motion with Dense Consistent Matchingcited by 15
- 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
- 2023Long-term Visual Localization with Mobile Sensorscited by 13
- 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
- 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
- 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
- 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
- 2023The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulationcited by 12
- 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
- 2023iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matchingcited by 12
- 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
- 20233D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimationcited by 11
- 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
- 2025Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Visioncited by 11
50 most cited of 156 All 156 (JSON)
- 2026MoSE3: Learning World-Space SE(3) at Every Pixel2 Oct 2026
- 2026GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking30 Sep 2026
- 2026LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation28 Sep 2026
- 2026Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models27 Sep 2026
- 2026AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos21 Sep 2026
- 2026CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts15 Sep 2026
- 2026Prior-free relative 6D pose estimation of multiple object instances8 Sep 2026
- 2026What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features3 Sep 2026
- 2026PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects17 Jul 2026
- 2026UniPose9D: Universal Category-Agnostic Object Pose Estimation10 Jul 2026
- 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation7 Jul 2026
- 2026Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space2 Jul 2026
38 more
- 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videos29 Jun 2026
- 2026Pose Anything Anywhere:Model-free Object Poses from Arbitrary References22 Jun 2026
- 2026Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation20 Jun 2026
- 2026Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models15 Jun 2026
- 2026ComPose: When to Trust Hands for Object Pose Tracking22 May 2026
- 2026RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos16 May 2026
- 2026Semantic Prior Guided One-View 6D Pose Estimation for Novel Objects7 May 2026
- 2026MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation22 Apr 2026
- 2026MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction29 Mar 2026
- 2026Object Pose Transformer: Unifying Unseen Object Pose Estimation24 Mar 2026
- 2026UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair20 Mar 2026
- 2026CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose7 Mar 2026
- 2026COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation28 Feb 2026
- 2026Research on a Camera Position Measurement Method based on a Parallel Perspective Error Transfer Model8 Feb 2026
- 2026IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and tools5 Feb 2026
- 2026Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception4 Feb 2026
- 2026HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos2 Feb 2026
- 2026OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Image12 Jan 2026
- 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation11 Jan 2026
- 2026Orient Anything V2: Unifying Orientation and Rotation Understanding9 Jan 2026
- 2025KV-Tracker: Real-Time Pose Tracking with Transformers27 Dec 2025
- 2025Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers21 Dec 2025
- 2025Light Field Based 6DoF Tracking of Previously Unobserved Objects15 Dec 2025
- 2025ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors9 Dec 2025
- 2025AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation19 Nov 2025
- 2025WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion19 Nov 2025
- 2025CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation17 Nov 2025
- 2025OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding16 Nov 2025
- 2025RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation21 Oct 2025
- 2025GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation19 Oct 2025
- 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference26 Sep 2025
- 2025IMD: A 6-DoF Pose Estimation Benchmark for Industrial Metallic Objects15 Sep 2025
- 2025GelSLAM: A Real-time, High-Fidelity, and Robust 3D Tactile SLAM System21 Aug 2025
- 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation21 Aug 2025
- 2025IntelliCap: Intelligent Guidance for Consistent View Sampling18 Aug 2025
- 2025Zero-shot Inexact CAD Model Alignment from a Single Image4 Jul 2025
- 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations1 Jul 2025
- 2025T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models24 Jun 2025
50 newest of 156 All 156 (JSON)
- 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimationcited by 10
- 2025PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Trackingcited by 5
- 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
- 2025HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimationcited by 4
- 2023PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registrationcited by 3
- 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priorscited by 2
- 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimationcited by 2
- 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generationcited by 0
- 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation21 Aug 2025
- 2025PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking29 Apr 2025
- 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation9 Mar 2025
- 2025HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation14 Feb 2025
- 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors12 Oct 2024
- 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation21 Mar 2024
- 2024Extreme Two-View Geometry From Object Poses with Diffusion Models5 Feb 2024
- 2023PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration11 Dec 2023
- 2023LightGlue: Local Feature Matching at Light Speedcited by 588
- 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 415
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 200
- 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 146
- 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 124
- 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
- 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
- 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
- 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 91
- 20243DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generationcited by 71
- 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
- 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
12 most cited of 144 All 144 (JSON)
- 2026MoSE3: Learning World-Space SE(3) at Every Pixel2 Oct 2026
- 2026GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking30 Sep 2026
- 2026LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimation28 Sep 2026
- 2026AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos21 Sep 2026
- 2026CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts15 Sep 2026
- 2026Prior-free relative 6D pose estimation of multiple object instances8 Sep 2026
- 2026What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features3 Sep 2026
- 2026PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects17 Jul 2026
- 2026UniPose9D: Universal Category-Agnostic Object Pose Estimation10 Jul 2026
- 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation7 Jul 2026
- 2026Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space2 Jul 2026
- 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videos29 Jun 2026
12 newest of 144 All 144 (JSON)