mlsanityData to 7 Oct 2026

SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects

arXiv 2308.16528 ↗First posted 31 Aug 2023cs.CV cs.LG cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

To enable meaningful robotic manipulation of objects in the real-world, 6D pose estimation is one of the critical aspects. Most existing approaches have difficulties to extend predictions to scenarios where novel object instances are continuously introduced, especially with heavy occlusions. In this work, we propose a few-shot pose estimation (FSPE) approach called SA6D, which uses a self-adaptive segmentation module to identify the novel target object and construct a point cloud model of the target object using only a small number of cluttered reference images. Unlike existing methods, SA6D does not require object-centric reference images or any additional object information, making it a more generalizable and scalable solution across categories. We evaluate SA6D on real-world tabletop object datasets and demonstrate that SA6D outperforms existing FSPE methods, particularly in cluttered scenes with occlusions, while requiring fewer reference images.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

37 of 48 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  4. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  5. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  6. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  7. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  8. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  9. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  10. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  11. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  12. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
25 more
  1. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  2. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  3. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  4. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  5. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  6. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  7. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  8. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  9. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  10. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  11. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  12. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  13. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  14. 2020Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentationcited by 64
  15. 2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
  16. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  17. 2019The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentationcited by 39
  18. 2023TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimationcited by 32
  19. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  20. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  21. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
  22. 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18
  23. 2022FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environmentscited by 8
  24. 2022Category-Agnostic 6D Pose Estimation with Conditional Neural Processescited by 4
  25. 2023Enhancing Interpretable Object Abstraction via Clustering-based Slot Initializationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 4.

6 papers.

  1. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  2. 2025ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Modelscited by 43
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  4. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  5. 2025PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimationcited by 5
  6. 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Referencecited by 1