# GeoNet: Deep Geodesic Networks for Point Cloud Analysis

arXiv: https://arxiv.org/abs/1901.00680 · HTML: https://mlsanity.com/paper/1901.00680/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2019.

## Built on by (most cited first, 11 of 11)

- [S4C: Self-Supervised Semantic Scene Completion with Neural Fields](https://mlsanity.com/paper/2310.07522/) (2023)
- [On the effectiveness of persistent homology](https://mlsanity.com/paper/2206.10551/) (2022)
- [PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling](https://mlsanity.com/paper/2204.10750/) (2022)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries](https://mlsanity.com/paper/2306.00658/) (2023)
- [Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination](https://mlsanity.com/paper/2305.16963/) (2023)
- [Surface-Aware Distilled 3D Semantic Features](https://mlsanity.com/paper/2503.18254/) (2025)
- ["Zero-Shot" Point Cloud Upsampling](https://mlsanity.com/paper/2106.13765/) (2021)
- [SN-Graph: a Minimalist 3D Object Representation for Classification](https://mlsanity.com/paper/2105.14784/) (2021)
- [GeoMM: On Geodesic Perspective for Multi-modal Learning](https://mlsanity.com/paper/2505.11216/) (2025)
- [Representation Learning of Point Cloud Upsampling in Global and Local Inputs](https://mlsanity.com/paper/2501.07076/) (2025)

## Abstract (arXiv)

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds. To demonstrate the applicability of learned geodesic-aware representations, we propose fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis. Our method improves the state-of-the-art on multiple representative tasks that can benefit from understandings of the underlying surface topology, including point upsampling, normal estimation, mesh reconstruction and non-rigid shape classification.