mlsanityData to 7 Oct 2026

CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration

arXiv 2103.06911 ↗First posted 11 Mar 2021cs.CV cs.ROcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper considers online object-level mapping using partial point-cloud observations obtained online in an unknown environment. We develop and approach for fully Convolutional Object Retrieval and Symmetry-AIded Registration (CORSAIR). Our model extends the Fully Convolutional Geometric Features model to learn a global object-shape embedding in addition to local point-wise features from the point-cloud observations. The global feature is used to retrieve a similar object from a category database, and the local features are used for robust pose registration between the observed and the retrieved object. Our formulation also leverages symmetries, present in the object shapes, to obtain promising local-feature pairs from different symmetry classes for matching. We present results from synthetic and real-world datasets with different object categories to verify the robustness of our method.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

26 of 34 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  8. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  9. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  10. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  11. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  12. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
14 more
  1. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  2. 2020Deep Global Registrationcited by 228
  3. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  4. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  5. 2016SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networkscited by 134
  6. 2018Fusion++: Volumetric Object-Level SLAMcited by 97
  7. 2018MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objectscited by 95
  8. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69
  9. 2020Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrievecited by 65
  10. 2020Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videoscited by 33
  11. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  12. 2020Deformation-Aware 3D Model Embedding and Retrievalcited by 30
  13. 2019Joint Embedding of 3D Scan and CAD Objectscited by 19
  14. 2021Fully Convolutional Geometric Features for Category-level Object Alignmentcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 1.

5 papers.

  1. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  2. 2022PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimationcited by 4
  3. 2022Accurate Instance-Level CAD Model Retrieval in a Large-Scale Databasecited by 3
  4. 2023From CAD models to soft point cloud labels: An automatic annotation pipeline for cheaply supervised 3D semantic segmentationcited by 1
  5. 2022Review on 6D Object Pose Estimation with the focus on Indoor Scene Understandingcited by 0