# Learning Compact Geometric Features

arXiv: https://arxiv.org/abs/1709.05056 · HTML: https://mlsanity.com/paper/1709.05056/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2017.

## Built on by (most cited first, 30 of 45)

- [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)
- [Equivariant Point Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2103.14147/) (2021)
- [CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence](https://mlsanity.com/paper/2207.05483/) (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)
- [Bootstrap Your Own Correspondences](https://mlsanity.com/paper/2106.00677/) (2021)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport](https://mlsanity.com/paper/2202.01537/) (2022)
- [PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds](https://mlsanity.com/paper/2110.01269/) (2021)
- [E2PN: Efficient SE(3)-Equivariant Point Network](https://mlsanity.com/paper/2206.05398/) (2022)
- [PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features](https://mlsanity.com/paper/2102.12093/) (2021)
- [Multiway Point Cloud Mosaicking with Diffusion and Global Optimization](https://mlsanity.com/paper/2404.00429/) (2024)
- [MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detection](https://mlsanity.com/paper/2408.00565/) (2024)
- [IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration](https://mlsanity.com/paper/2111.09624/) (2021)
- [Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks](https://mlsanity.com/paper/2103.15226/) (2021)
- [RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation](https://mlsanity.com/paper/2104.05328/) (2021)
- [City-scale Scene Change Detection using Point Clouds](https://mlsanity.com/paper/2103.14314/) (2021)
- [Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2108.02613/) (2021)
- [WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration](https://mlsanity.com/paper/2108.02740/) (2021)
- [CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance](https://mlsanity.com/paper/2203.09887/) (2022)
- [Generalizable Local Feature Pre-training for Deformable Shape Analysis](https://mlsanity.com/paper/2303.15104/) (2023)
- [CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame](https://mlsanity.com/paper/2303.03101/) (2023)
- [KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping](https://mlsanity.com/paper/2309.15394/) (2023)
- [Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds](https://mlsanity.com/paper/2210.14899/) (2022)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [(Just) A Spoonful of Refinements Helps the Registration Error Go Down](https://mlsanity.com/paper/2108.03257/) (2021)
- [Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine](https://mlsanity.com/paper/2111.10817/) (2021)
- [RoCNet: 3D Robust Registration of Point-Clouds using Deep Learning](https://mlsanity.com/paper/2303.07963/) (2023)

## Abstract (arXiv)

We present an approach to learning features that represent the local geometry around a point in an unstructured point cloud. Such features play a central role in geometric registration, which supports diverse applications in robotics and 3D vision. Current state-of-the-art local features for unstructured point clouds have been manually crafted and none combines the desirable properties of precision, compactness, and robustness. We show that features with these properties can be learned from data, by optimizing deep networks that map high-dimensional histograms into low-dimensional Euclidean spaces. The presented approach yields a family of features, parameterized by dimension, that are both more compact and more accurate than existing descriptors.