mlsanityData to 7 Oct 2026

PREDATOR: Registration of 3D Point Clouds with Low Overlap

arXiv 2011.13005 ↗First posted 25 Nov 2020cs.CV eess.IVcited by 287

Not on the map. Why?

Abstract (arXiv)

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20% in the low-overlap scenario, and also sets a new state of the art for the 3DMatch benchmark with 89% registration recall.

Key facts. Cited by 287 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 45; 2023: 62; 2024: 60; 2025: 57; 2026: 35.

287 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  3. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  4. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  5. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  6. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  7. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  8. 20233D Registration with Maximal Cliquescited by 83
  9. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 83
  10. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  11. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  12. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 68
38 more
  1. 2023Neural LiDAR Fields for Novel View Synthesiscited by 65
  2. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  3. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
  4. 2021DPFM: Deep Partial Functional Mapscited by 58
  5. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  6. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  7. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  8. 2022CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondencecited by 43
  9. 2022nerf2nerf: Pairwise Registration of Neural Radiance Fieldscited by 39
  10. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  11. 2022Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detectioncited by 34
  12. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  13. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  14. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  15. 2022Generalized Differentiable RANSACcited by 30
  16. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  17. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  18. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  19. 2021MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Squarecited by 27
  20. 20232D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Cloudscited by 27
  21. 2023Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registrationcited by 26
  22. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 26
  23. 2022RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registrationcited by 25
  24. 2021Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representationscited by 24
  25. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  26. 2024An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Modelscited by 22
  27. 2023DReg-NeRF: Deep Registration for Neural Radiance Fieldscited by 21
  28. 2023NICP: Neural ICP for 3D Human Registration at Scalecited by 21
  29. 2021PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Cloudscited by 20
  30. 2022Reliable Inlier Evaluation for Unsupervised Point Cloud Registrationcited by 19
  31. 2022PeRFception: Perception using Radiance Fieldscited by 19
  32. 2022E2PN: Efficient SE(3)-Equivariant Point Networkcited by 17
  33. 2022ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairscited by 17
  34. 2023Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweightingcited by 17
  35. 2023DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matchingcited by 17
  36. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
  37. 2024FastMAC: Stochastic Spectral Sampling of Correspondence Graphcited by 16
  38. 2024KISS-Matcher: Fast and Robust Point Cloud Registration Revisitedcited by 16

50 most cited of 287 All 287 (JSON)