# PREDATOR: Registration of 3D Point Clouds with Low Overlap

arXiv: https://arxiv.org/abs/2011.13005 · HTML: https://mlsanity.com/paper/2011.13005/

## Key facts

- Cited by 290 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 30 of 290)

- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation](https://mlsanity.com/paper/2311.15707/) (2023)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [Lepard: Learning partial point cloud matching in rigid and deformable scenes](https://mlsanity.com/paper/2111.12591/) (2021)
- [3D Registration with Maximal Cliques](https://mlsanity.com/paper/2305.10854/) (2023)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [FS6D: Few-Shot 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2203.14628/) (2022)
- [Rotation-Invariant Transformer for Point Cloud Matching](https://mlsanity.com/paper/2303.08231/) (2023)
- [You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors](https://mlsanity.com/paper/2109.00182/) (2021)
- [Neural LiDAR Fields for Novel View Synthesis](https://mlsanity.com/paper/2305.01643/) (2023)
- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://mlsanity.com/paper/2203.14453/) (2022)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [DPFM: Deep Partial Functional Maps](https://mlsanity.com/paper/2110.09994/) (2021)
- [FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models](https://mlsanity.com/paper/2312.00947/) (2023)
- [Deep Hough Voting for Robust Global Registration](https://mlsanity.com/paper/2109.04310/) (2021)
- [Is Geometry Enough for Matching in Visual Localization?](https://mlsanity.com/paper/2203.12979/) (2022)
- [CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence](https://mlsanity.com/paper/2207.05483/) (2022)
- [nerf2nerf: Pairwise Registration of Neural Radiance Fields](https://mlsanity.com/paper/2211.01600/) (2022)
- [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://mlsanity.com/paper/2303.12384/) (2023)
- [Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection](https://mlsanity.com/paper/2211.00191/) (2022)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [Robust Outlier Rejection for 3D Registration with Variational Bayes](https://mlsanity.com/paper/2304.01514/) (2023)
- [Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization](https://mlsanity.com/paper/2111.12878/) (2021)
- [Generalized Differentiable RANSAC](https://mlsanity.com/paper/2212.13185/) (2022)
- [SGAligner : 3D Scene Alignment with Scene Graphs](https://mlsanity.com/paper/2304.14880/) (2023)
- [Jigsaw: Learning to Assemble Multiple Fractured Objects](https://mlsanity.com/paper/2305.17975/) (2023)
- [A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling](https://mlsanity.com/paper/2312.02719/) (2023)

## 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.