mlsanityData to 7 Oct 2026

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

arXiv 2203.14628 ↗First posted 28 Mar 2022cs.CV cs.ROcited by 81

Not on the map. Why?

Abstract (arXiv)

6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models. In this work, we study a new open set problem; the few-shot 6D object poses estimation: estimating the 6D pose of an unknown object by a few support views without extra training. To tackle the problem, we point out the importance of fully exploring the appearance and geometric relationship between the given support views and query scene patches and propose a dense prototypes matching framework by extracting and matching dense RGBD prototypes with transformers. Moreover, we show that the priors from diverse appearances and shapes are crucial to the generalization capability under the problem setting and thus propose a large-scale RGBD photorealistic dataset (ShapeNet6D) for network pre-training. A simple and effective online texture blending approach is also introduced to eliminate the domain gap from the synthesis dataset, which enriches appearance diversity at a low cost. Finally, we discuss possible solutions to this problem and establish benchmarks on popular datasets to facilitate future research. The project page is at urlhttps://fs6d.github.io/.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 48 of its 70 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

48 of 70 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  9. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  10. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  11. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
36 more
  1. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  2. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  3. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  4. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  5. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  6. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  7. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  8. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  9. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  10. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  11. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  12. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  13. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 175
  14. 2018Neighbourhood Consensus Networkscited by 173
  15. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  16. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  17. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  18. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  19. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  20. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  21. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  22. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  23. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  24. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  25. 2020Dual-Resolution Correspondence Networkscited by 90
  26. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  27. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  28. 2019USIP: Unsupervised Stable Interest Point Detection from 3D Point Cloudscited by 70
  29. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  30. 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
  31. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  32. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  33. 2017Going Further with Point Pair Featurescited by 28
  34. 2020Distinctive 3D local deep descriptorscited by 21
  35. 2021iShape: A First Step Towards Irregular Shape Instance Segmentationcited by 12
  36. 2022Towards Self-Supervised Category-Level Object Pose and Size Estimationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 26; 2024: 17; 2025: 21; 2026: 12.

81 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  3. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  4. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  5. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  6. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  7. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  8. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  9. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  10. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  11. 2023TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimationcited by 32
  12. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
38 more
  1. 2023Open-vocabulary object 6D pose estimationcited by 29
  2. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  3. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  4. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  5. 2023Pre-training on Synthetic Driving Data for Trajectory Predictioncited by 18
  6. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
  7. 2024AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Waycited by 15
  8. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
  9. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  10. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  11. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  12. 2025Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Visioncited by 11
  13. 2023MFOS: Model-Free & One-Shot Object Pose Estimationcited by 10
  14. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimationcited by 10
  15. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  16. 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 10
  17. 20256D Object Pose Tracking in Internet Videos for Robotic Manipulationcited by 10
  18. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
  19. 2025UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial Referencescited by 9
  20. 2025Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perceptioncited by 9
  21. 2023You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Examplecited by 8
  22. 2023VoxDet: Voxel Learning for Novel Instance Detectioncited by 8
  23. 2023KeyMatchNet: Zero-Shot Pose Estimation in 3D Point Clouds by Generalized Keypoint Matchingcited by 7
  24. 2025PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Imagecited by 7
  25. 2023SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objectscited by 6
  26. 2025PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Trackingcited by 5
  27. 2025ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectorscited by 5
  28. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  29. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  30. 2025HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimationcited by 4
  31. 2023Digital Twin Tracking Dataset (DTTD): A New RGB+Depth 3D Dataset for Longer-Range Object Tracking Applicationscited by 3
  32. 2023Learning Better Keypoints for Multi-Object 6DoF Pose Estimationcited by 3
  33. 2024Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometriescited by 3
  34. 2024Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimationcited by 3
  35. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  36. 2023Generalizable Pose Estimation Using Implicit Scene Representationscited by 2
  37. 2023S2P3: Self-Supervised Polarimetric Pose Predictioncited by 2
  38. 2024Bayesian Inverse Graphics for Few-Shot Concept Learningcited by 2

50 most cited of 81 All 81 (JSON)