mlsanityData to 14 Oct 2026

Any6D: Model-free 6D Pose Estimation of Novel Objects

arXiv 2503.18673 ↗First posted 24 Mar 2025cs.CV cs.AI cs.ROcited by 49

Not on the map. Why?

Abstract (arXiv)

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike existing methods that rely on textured 3D models or multiple viewpoints, Any6D leverages a joint object alignment process to enhance 2D-3D alignment and metric scale estimation for improved pose accuracy. Our approach integrates a render-and-compare strategy to generate and refine pose hypotheses, enabling robust performance in scenarios with occlusions, non-overlapping views, diverse lighting conditions, and large cross-environment variations. We evaluate our method on five challenging datasets: REAL275, Toyota-Light, HO3D, YCBINEOAT, and LM-O, demonstrating its effectiveness in significantly outperforming state-of-the-art methods for novel object pose estimation. Project page: https://taeyeop.com/any6d

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 66 of its 78 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

66 of 78 references.

References · 66

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  3. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  8. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  10. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  11. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  12. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
38 more
  1. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  2. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  3. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  4. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  5. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  6. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  7. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  8. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  9. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  10. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  11. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 184
  12. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  13. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  14. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  15. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  16. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  17. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  18. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  19. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  20. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  21. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  22. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  23. 2018MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objectscited by 95
  24. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 90
  25. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 87
  26. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  27. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  28. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  29. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  30. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  31. 2025OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraintscited by 59
  32. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  33. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  34. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 50
  35. 2024Introducing HOT3D: An Egocentric Dataset for 3D Hand and Object Trackingcited by 48
  36. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  37. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 42
  38. 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 38.

49 papers.

Sort:

By area:

  1. 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
  2. 2026Do as I Do: Dexterous Manipulation Data from Everyday Human Videoscited by 13
  3. 2025DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videoscited by 10
  4. 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videoscited by 7
  5. 2026Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observationscited by 7
  6. 2025ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectorscited by 5
  7. 2026FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulationcited by 5
  8. 2026ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactionscited by 4
  9. 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translationcited by 3
  10. 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimationcited by 2
  11. 2025DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulationcited by 2
  12. 2025Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single Viewcited by 2
37 more
  1. 2026Event6D: Event-based Novel Object 6D Pose Trackingcited by 2
  2. 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modelingcited by 2
  3. 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Referencecited by 1
  4. 2025CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generationcited by 1
  5. 2025IGen: Scalable Data Generation for Robot Learning from Open-World Imagescited by 1
  6. 2026Reliability-aware Execution Gating for Near-field and Off-axis Vision-guided Robotic Alignmentcited by 1
  7. 2026CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Posecited by 1
  8. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  9. 2026Mind the Shape Gap: A Benchmark and Baseline for Deformation-Aware 6D Pose Estimation of Agricultural Producecited by 1
  10. 2026AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videoscited by 1
  11. 2026DexAgent: An Agentic Human2Sim2Robot Framework for Dexterous Manipulation with Self-Evolving Tool Librarycited by 1
  12. 2025Color-Pair Guided Robust Zero-Shot 6D Pose Estimation and Tracking of Cluttered Objects on Edge Devicescited by 0
  13. 2025AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulationcited by 0
  14. 2026A Mixed Reality System for Robust Manikin Localization in Childbirth Trainingcited by 0
  15. 2026TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localizationcited by 0
  16. 2026UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Paircited by 0
  17. 2026Object Pose Transformer: Unifying Unseen Object Pose Estimationcited by 0
  18. 2026Exploring 6D Object Pose Estimation with Deformationcited by 0
  19. 2026MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimationcited by 0
  20. 2026Semantic Prior Guided One-View 6D Pose Estimation for Novel Objectscited by 0
  21. 2026RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videoscited by 0
  22. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0
  23. 2026MooMIns -- Monocular 3D Reconstruction and Object Pose Estimation from Multiple Instancescited by 0
  24. 2026Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimationcited by 0
  25. 2026Pose Anything Anywhere:Model-free Object Poses from Arbitrary Referencescited by 0
  26. 2026MF-UAVPose6D: A Model-Free Monocular 6-DoF Pose Estimation Framework for Fixed-Wing UAVscited by 0
  27. 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videoscited by 0
  28. 2026UniPose9D: Universal Category-Agnostic Object Pose Estimationcited by 0
  29. 2026SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignmentcited by 0
  30. 2026Detecting Pose Estimation Failures via Keypoint Self-Consistencycited by 0
  31. 2026CLON: Cue-Calibrated Linguistic Object Onboarding for Zero-Shot 6D Pose Front-Endscited by 0
  32. 2026AURORA: Active Uncertainty-Driven Re-Orientation for In-Hand Reconstructioncited by 0
  33. 2026Track, Articulate, Act: Generating Articulation from Casual Human Videoscited by 0
  34. 2026LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimationcited by 0
  35. 2026GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Trackingcited by 0
  36. 2026NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinementcited by 0
  37. 2026ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learningcited by 0