mlsanityData to 14 Oct 2026

You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example

arXiv 2305.12626 ↗First posted 22 May 2023cs.RO cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

In order to meaningfully interact with the world, robot manipulators must be able to interpret objects they encounter. A critical aspect of this interpretation is pose estimation: inferring quantities that describe the position and orientation of an object in 3D space. Most existing approaches to pose estimation make limiting assumptions, often working only for specific, known object instances, or at best generalising to an object category using large pose-labelled datasets. In this work, we present a method for achieving category-level pose estimation by inspection of just a single object from a desired category. We show that we can subsequently perform accurate pose estimation for unseen objects from an inspected category, and considerably outperform prior work by exploiting multi-view correspondences. We demonstrate that our method runs in real-time, enabling a robot manipulator equipped with an RGBD sensor to perform online 6D pose estimation for novel objects. Finally, we showcase our method in a continual learning setting, with a robot able to determine whether objects belong to known categories, and if not, use active perception to produce a one-shot category representation for subsequent pose estimation.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

38 of 46 references.

References · 38

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  2. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  4. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  7. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  8. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  9. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 209
  10. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  11. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  12. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
26 more
  1. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  2. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 153
  3. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 142
  4. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  5. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  6. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  7. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  8. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  9. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  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. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  14. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  15. 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
  16. 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42
  17. 2021NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimationcited by 41
  18. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  19. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  20. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  21. 2018Category-level 6D Object Pose Recovery in Depth Imagescited by 21
  22. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19
  23. 2021Optimal Pose and Shape Estimation for Category-level 3D Object Perceptioncited by 15
  24. 2021Online Object Model Reconstruction and Reuse for Lifelong Improvement of Robot Manipulationcited by 10
  25. 2022ReorientBot: Learning Object Reorientation for Specific-Posed Placementcited by 10
  26. 2015Inferring 3D Object Pose in RGB-D Imagescited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 6.

8 papers.

  1. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  2. 2024DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Modelscited by 44
  3. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 25
  4. 2024Composable Part-Based Manipulationcited by 17
  5. 2023NOVUM: Neural Object Volumes for Robust Object Classificationcited by 11
  6. 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimationcited by 10
  7. 2024Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videoscited by 5
  8. 2024Adapting Skills to Novel Grasps: A Self-Supervised Approachcited by 0