mlsanityData to 7 Oct 2026

Canonical mapping as a general-purpose object descriptor for robotic manipulation

arXiv 2303.01331 ↗First posted 2 Mar 2023cs.RO cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Perception is an essential part of robotic manipulation in a semi-structured environment. Traditional approaches produce a narrow task-specific prediction (e.g., object's 6D pose), that cannot be adapted to other tasks and is ill-suited for deformable objects. In this paper, we propose using canonical mapping as a near-universal and flexible object descriptor. We demonstrate that common object representations can be derived from a single pre-trained canonical mapping model, which in turn can be generated with minimal manual effort using an automated data generation and training pipeline. We perform a multi-stage experiment using two robot arms that demonstrate the robustness of the perception approach and the ways it can inform the manipulation strategy, thus serving as a powerful foundation for general-purpose robotic manipulation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

17 of 20 references.

References · 17

  1. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  2. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  3. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  4. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  5. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  6. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  7. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  8. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  9. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  10. 2020Articulation-aware Canonical Surface Mappingcited by 80
  11. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  12. 2020Continuous Surface Embeddingscited by 79
5 more
  1. 2019Canonical Surface Mapping via Geometric Cycle Consistencycited by 62
  2. 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42
  3. 2016Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimationcited by 34
  4. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  5. 2020GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervisioncited by 28

Built on by

Not cited yet.