# Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds

arXiv: https://arxiv.org/abs/2210.14899 · HTML: https://mlsanity.com/paper/2210.14899/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 73 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [3D-CODED : 3D Correspondences by Deep Deformation](https://mlsanity.com/paper/1806.05228/) (2018)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence](https://mlsanity.com/paper/2003.14286/) (2020)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://mlsanity.com/paper/1908.06297/) (2019)
- [Effective Rotation-invariant Point CNN with Spherical Harmonics kernels](https://mlsanity.com/paper/1906.11555/) (2019)
- [End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds](https://mlsanity.com/paper/2003.05855/) (2020)
- [CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds](https://mlsanity.com/paper/2012.15638/) (2020)

## Built on by (most cited first, 3 of 3)

- [PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer](https://mlsanity.com/paper/2404.14034/) (2024)
- [Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration](https://mlsanity.com/paper/2307.07142/) (2023)
- [Multi-Representation Geometric Hierarchy Fusion: An Implicit-Submap Driven Framework for Resilient 3D Place Recognition](https://mlsanity.com/paper/2506.14243/) (2025)

## Abstract (arXiv)

Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently across different 3D point clouds. Therefore these too accurate features may play a counterproductive role due to the inconsistent point feature representations of correspondences caused by the unpredictable noise, partiality, deformation, etc, in the local geometry. In this paper, we propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference. Born with an Encoder and a Dynamic Fusion module, our method EDFNet develops from two aspects. First, we augment the matchability of correspondences by utilizing their repetitive local structure. To this end, a special encoder is designed to exploit two input point clouds jointly for each point descriptor. It not only captures the local geometry of each point in the current point cloud by convolution, but also exploits the repetitive structure from paired point cloud by Transformer. Second, we propose a dynamical fusion module to jointly use different scale features. There is an inevitable struggle between robustness and discriminativeness of the single scale feature. Specifically, the small scale feature is robust since little interference exists in this small receptive field. But it is not sufficiently discriminative as there are many repetitive local structures within a point cloud. Thus the resultant descriptors will lead to many incorrect matches. In contrast, the large scale feature is more discriminative by integrating more neighborhood information. ...