# GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2312.00068 · HTML: https://mlsanity.com/paper/2312.00068/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 24 of 24)

- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way](https://mlsanity.com/paper/2209.15397/) (2022)
- [Topological Autoencoders](https://mlsanity.com/paper/1906.00722/) (2019)
- [Deep Learning with Topological Signatures](https://mlsanity.com/paper/1707.04041/) (2017)
- [PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks](https://mlsanity.com/paper/1912.03264/) (2019)
- [Learning to Generate Realistic LiDAR Point Clouds](https://mlsanity.com/paper/2209.03954/) (2022)
- [Topological Graph Neural Networks](https://mlsanity.com/paper/2102.07835/) (2021)
- [A Topology Layer for Machine Learning](https://mlsanity.com/paper/1905.12200/) (2019)
- [UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation](https://mlsanity.com/paper/2311.01448/) (2023)
- [Deep Generative Modeling of LiDAR Data](https://mlsanity.com/paper/1812.01180/) (2018)
- [Unsupervised 3D Shape Completion through GAN Inversion](https://mlsanity.com/paper/2104.13366/) (2021)
- [A Topological Regularizer for Classifiers via Persistent Homology](https://mlsanity.com/paper/1806.10714/) (2018)
- [Object DGCNN: 3D Object Detection using Dynamic Graphs](https://mlsanity.com/paper/2110.06923/) (2021)
- [NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields](https://mlsanity.com/paper/2304.14811/) (2023)
- [To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels](https://mlsanity.com/paper/2106.13381/) (2021)
- [Explicit topological priors for deep-learning based image segmentation using persistent homology](https://mlsanity.com/paper/1901.10244/) (2019)
- [Topology-Aware Surface Reconstruction for Point Clouds](https://mlsanity.com/paper/1811.12543/) (2018)
- [Persistent homology machine learning for fingerprint classification](https://mlsanity.com/paper/1711.09158/) (2017)
- [CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm](https://mlsanity.com/paper/2207.05359/) (2022)
- [Applying Topological Persistence in Convolutional Neural Network for Music Audio Signals](https://mlsanity.com/paper/1608.07373/) (2016)
- [Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space](https://mlsanity.com/paper/1809.10239/) (2018)
- [Characterizing the Shape of Activation Space in Deep Neural Networks](https://mlsanity.com/paper/1901.09496/) (2019)
- [DSLR: Dynamic to Static LiDAR Scan Reconstruction Using Adversarially Trained Autoencoder](https://mlsanity.com/paper/2105.12774/) (2021)

## Built on by (most cited first, 2 of 2)

- [SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections](https://mlsanity.com/paper/2504.03089/) (2025)
- [A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams](https://mlsanity.com/paper/2512.12410/) (2025)

## Abstract (arXiv)

Sparse LiDAR point clouds cause severe loss of detail of static structures and reduce the density of static points available for navigation. Reduced density can be detrimental to navigation under several scenarios. We observe that despite high sparsity, in most cases, the global topology of LiDAR outlining the static structures can be inferred. We utilize this property to obtain a backbone skeleton of a LiDAR scan in the form of a single connected component that is a proxy to its global topology. We utilize the backbone to augment new points along static structures to overcome sparsity. Newly introduced points could correspond to existing static structures or to static points that were earlier obstructed by dynamic objects. To the best of our knowledge, we are the first to use such a strategy for sparse LiDAR point clouds. Existing solutions close to our approach fail to identify and preserve the global static LiDAR topology and generate sub-optimal points. We propose GLiDR, a Graph Generative network that is topologically regularized using 0-dimensional Persistent Homology (PH) constraints. This enables GLiDR to introduce newer static points along a topologically consistent global static LiDAR backbone. GLiDR generates precise static points using 32× sparser dynamic scans and performs better than the baselines across three datasets. GLiDR generates a valuable byproduct - an accurate binary segmentation mask of static and dynamic objects that are helpful for navigation planning and safety in constrained environments. The newly introduced static points allow GLiDR to outperform LiDAR-based navigation using SLAM in several settings. Source code is available at https://kshitijbhat.github.io/glidr