# Large-scale 3D point cloud representations via graph inception networks with applications to autonomous driving

arXiv: https://arxiv.org/abs/1906.11359 · HTML: https://mlsanity.com/paper/1906.11359/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds](https://mlsanity.com/paper/2109.00113/) (2021)
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://mlsanity.com/paper/2108.04023/) (2021)
- [Affinity-Aware Graph Networks](https://mlsanity.com/paper/2206.11941/) (2022)
- [Rate-Distortion Optimized Skip Coding of Region Adaptive Hierarchical Transform Coefficients for MPEG G-PCC](https://mlsanity.com/paper/2412.05574/) (2024)
- [PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification](https://mlsanity.com/paper/2403.06698/) (2024)
- [3D Point Cloud Compression with Recurrent Neural Network and Image Compression Methods](https://mlsanity.com/paper/2402.11680/) (2024)
- [SF3D-RGB: Scene Flow Estimation from Monocular Camera and Sparse LiDAR](https://mlsanity.com/paper/2602.21699/) (2026)

## Abstract (arXiv)

We present a novel graph-neural-network-based system to effectively represent large-scale 3D point clouds with the applications to autonomous driving. Many previous works studied the representations of 3D point clouds based on two approaches, voxelization, which causes discretization errors and learning, which is hard to capture huge variations in large-scale scenarios. In this work, we combine voxelization and learning: we discretize the 3D space into voxels and propose novel graph inception networks to represent 3D points in each voxel. This combination makes the system avoid discretization errors and work for large-scale scenarios. The entire system for large-scale 3D point clouds acts like the blocked discrete cosine transform for 2D images; we thus call it the point cloud neural transform (PCT). We further apply the proposed PCT to represent real-time LiDAR sweeps produced by self-driving cars and the PCT with graph inception networks significantly outperforms its competitors.