mlsanityData to 7 Oct 2026

MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World

arXiv 2203.15309 ↗First posted 29 Mar 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in the presence of real-world data. We thus analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds, and the sensitivity of the widely-used SVD-based loss function to the range of rotation between the two point clouds. We address the first challenge by introducing a new normalization strategy, Match Normalization, and the second via the use of a loss function based on the negative log likelihood of point correspondences. Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM. Our experiments on the real-scene TUD-L, LINEMOD and Occluded-LINEMOD datasets evidence the benefits of our strategies. They allow for the first time learning-based 3D object registration methods to achieve meaningful results on real-world data. We therefore expect them to be key to the future development of point cloud registration methods.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 40 of its 76 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

40 of 76 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2017Deep Setscited by 1,394
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  11. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
28 more
  1. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  2. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  3. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  4. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  5. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  6. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  7. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  8. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  9. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  10. 2020Deep Global Registrationcited by 228
  11. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  12. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  13. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  14. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  15. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  16. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  17. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  18. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  19. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  20. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  21. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  22. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  23. 2016SE-Sync: A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Groupcited by 80
  24. 2019A Polynomial-time Solution for Robust Registration with Extreme Outlier Ratescited by 38
  25. 2019Backpropagation-Friendly Eigendecompositioncited by 27
  26. 2019SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondencescited by 26
  27. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20
  28. 2018Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Lossescited by 15

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 3; 2025: 3.

13 papers.

Sort:

By area:

  1. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 32
  2. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  3. 20223D Vision with Transformers: A Surveycited by 21
  4. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  5. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  6. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  7. 2022Geo6D: Geometric Constraints Learning for 6D Pose Estimationcited by 2
  8. 2024Registering Neural 4D Gaussians for Endoscopic Surgerycited by 2
  9. 2023AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registrationcited by 1
  10. 2024Correspondence Free Multivector Cloud Registration using Conformal Geometric Algebracited by 0
  11. 2024Level-Set Parameters: Novel Representation for 3D Shape Analysiscited by 0
  12. 2025DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarioscited by 0
1 more
  1. 2025iMatcher: Improve matching in point cloud registration via local-to-global geometric consistency learningcited by 0