# The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

arXiv: https://arxiv.org/abs/1811.06879 · HTML: https://mlsanity.com/paper/1811.06879/

## Key facts

- Cited by 169 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2018.

## Built on by (most cited first, 30 of 169)

- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [Frame Averaging for Invariant and Equivariant Network Design](https://mlsanity.com/paper/2110.03336/) (2021)
- [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)
- [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)
- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (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)
- [Equivariant Point Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2103.14147/) (2021)
- [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)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [DeepI2P: Image-to-Point Cloud Registration via Deep Classification](https://mlsanity.com/paper/2104.03501/) (2021)
- [DPFM: Deep Partial Functional Maps](https://mlsanity.com/paper/2110.09994/) (2021)
- [Deep Hough Voting for Robust Global Registration](https://mlsanity.com/paper/2109.04310/) (2021)
- [Point-set Distances for Learning Representations of 3D Point Clouds](https://mlsanity.com/paper/2102.04014/) (2021)
- [HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions](https://mlsanity.com/paper/2308.01477/) (2023)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence](https://mlsanity.com/paper/2207.05483/) (2022)
- [Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors](https://mlsanity.com/paper/2205.14886/) (2022)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [Learning general and distinctive 3D local deep descriptors for point cloud registration](https://mlsanity.com/paper/2105.10382/) (2021)
- [nerf2nerf: Pairwise Registration of Neural Radiance Fields](https://mlsanity.com/paper/2211.01600/) (2022)
- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching](https://mlsanity.com/paper/2312.04060/) (2023)
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [Bootstrap Your Own Correspondences](https://mlsanity.com/paper/2106.00677/) (2021)
- [2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds](https://mlsanity.com/paper/2308.05667/) (2023)

## Abstract (arXiv)

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers using a voxelized smoothed density value (SDV) representation. The latter is computed per interest point and aligned to the local reference frame (LRF) to achieve rotation invariance. Our compact, learned, rotation invariant 3D point cloud descriptor achieves 94.9% average recall on the 3DMatch benchmark data set, outperforming the state-of-the-art by more than 20 percent points with only 32 output dimensions. This very low output dimension allows for near realtime correspondence search with 0.1 ms per feature point on a standard PC. Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers. We show that 3DSmoothNet trained only on RGB-D indoor scenes of buildings achieves 79.0% average recall on laser scans of outdoor vegetation, more than double the performance of our closest, learning-based competitors. Code, data and pre-trained models are available online at https://github.com/zgojcic/3DSmoothNet.