mlsanityData to 14 Oct 2026

Fully Convolutional Geometric Features for Category-level Object Alignment

arXiv 2103.04494 ↗First posted 8 Mar 2021cs.CV cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper focuses on pose registration of different object instances from the same category. This is required in online object mapping because object instances detected at test time usually differ from the training instances. Our approach transforms instances of the same category to a normalized canonical coordinate frame and uses metric learning to train fully convolutional geometric features. The resulting model is able to generate pairs of matching points between the instances, allowing category-level registration. Evaluation on both synthetic and real-world data shows that our method provides robust features, leading to accurate alignment of instances with different shapes.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

22 of 37 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017Mask R-CNNcited by 7,277
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  9. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  11. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
10 more
  1. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  2. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  3. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  4. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  5. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  6. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  7. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  8. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 103
  9. 20176-DoF Object Pose from Semantic Keypointscited by 89
  10. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 0; 2025: 1.

6 papers.

  1. 2021Optimal Pose and Shape Estimation for Category-level 3D Object Perceptioncited by 15
  2. 2022Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypointscited by 7
  3. 2023Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimationcited by 7
  4. 2021CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registrationcited by 5
  5. 2022Accurate Instance-Level CAD Model Retrieval in a Large-Scale Databasecited by 3
  6. 2025Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimationcited by 0