mlsanityData to 7 Oct 2026

FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models

arXiv 2312.00947 ↗First posted 1 Dec 2023cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Estimating the 6D pose of objects unseen during training is highly desirable yet challenging. Zero-shot object 6D pose estimation methods address this challenge by leveraging additional task-specific supervision provided by large-scale, photo-realistic synthetic datasets. However, their performance heavily depends on the quality and diversity of rendered data and they require extensive training. In this work, we show how to tackle the same task but without training on specific data. We propose FreeZe, a novel solution that harnesses the capabilities of pre-trained geometric and vision foundation models. FreeZe leverages 3D geometric descriptors learned from unrelated 3D point clouds and 2D visual features learned from web-scale 2D images to generate discriminative 3D point-level descriptors. We then estimate the 6D pose of unseen objects by 3D registration based on RANSAC. We also introduce a novel algorithm to solve ambiguous cases due to geometrically symmetric objects that is based on visual features. We comprehensively evaluate FreeZe across the seven core datasets of the BOP Benchmark, which include over a hundred 3D objects and 20,000 images captured in various scenarios. FreeZe consistently outperforms all state-of-the-art approaches, including competitors extensively trained on synthetic 6D pose estimation data. Code will be publicly available at https://andreacaraffa.github.io/freeze.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 42 of its 60 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

42 of 60 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  7. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  10. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  11. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  12. 2023Fast Segment Anythingcited by 286
30 more
  1. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  2. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  3. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  4. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  5. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  6. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  7. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 141
  8. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  9. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  10. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 113
  11. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  12. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  13. 20183D Point Capsule Networkscited by 106
  14. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  15. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 86
  16. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  17. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  18. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  19. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  20. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  21. 2020End-to-End Learning Local Multi-view Descriptors for 3D Point Cloudscited by 47
  22. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  23. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 41
  24. 2021ZePHyR: Zero-shot Pose Hypothesis Ratingcited by 26
  25. 2017Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Imagescited by 15
  26. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  27. 2023You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Examplecited by 8
  28. 2021WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registrationcited by 7
  29. 2023Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimationcited by 7
  30. 2023SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objectscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 29; 2026: 22.

56 papers.

Sort:

By area:

  1. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  2. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  3. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  4. 2025BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimationcited by 18
  5. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
  6. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 16
  7. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
  8. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  9. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  10. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  11. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  12. 2025UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial Referencescited by 9
38 more
  1. 2025PoseTraj: Pose-Aware Trajectory Control in Video Diffusioncited by 7
  2. 2025Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulationcited by 6
  3. 2025ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectorscited by 5
  4. 2025Distilling 3D distinctive local descriptors for 6D pose estimationcited by 4
  5. 2024Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimationcited by 3
  6. 2025A dataset-free approach for self-supervised learning of 3D reflectional symmetriescited by 3
  7. 2025CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settingscited by 2
  8. 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimationcited by 2
  9. 2026OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Imagecited by 2
  10. 2025Zero-shot Inexact CAD Model Alignment from a Single Imagecited by 1
  11. 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Referencecited by 1
  12. 2025CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generationcited by 1
  13. 2025Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Cloudscited by 1
  14. 2026IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and toolscited by 1
  15. 2026COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimationcited by 1
  16. 2024Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Referencecited by 0
  17. 2025DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarioscited by 0
  18. 2025GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexitycited by 0
  19. 2025RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Basecited by 0
  20. 2025OPFormer: Object Pose Estimation leveraging foundation model with geometric encodingcited by 0
  21. 2025WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusioncited by 0
  22. 2025SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Pickingcited by 0
  23. 2025Geo6DPose: Fast Zero-Shot 6D Object Pose Estimation via Geometry-Filtered Feature Matchingcited by 0
  24. 2025PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoningcited by 0
  25. 2025AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignmentcited by 0
  26. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0
  27. 2026Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perceptioncited by 0
  28. 2026Training-free Detection and 6D Pose Estimation of Unseen Surgical Instrumentscited by 0
  29. 2026MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimationcited by 0
  30. 2026RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videoscited by 0
  31. 2026Object Pose and Shape Estimation for Grasping: Does it Work?cited by 0
  32. 2026Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learningcited by 0
  33. 2026TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimationcited by 0
  34. 2026MooMIns -- Monocular 3D Reconstruction and Object Pose Estimation from Multiple Instancescited by 0
  35. 2026Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimationcited by 0
  36. 2026Pose Anything Anywhere:Model-free Object Poses from Arbitrary Referencescited by 0
  37. 2026xperception -- Making Robotic Grasping Easiercited by 0
  38. 2026RRTrack: Robust and Recoverable Object 6D Pose Tracking for Dynamic Scenescited by 0

50 most cited of 56 All 56 (JSON)