# Efficient LiDAR Point Cloud Geometry Compression Through Neighborhood Point Attention

arXiv: https://arxiv.org/abs/2208.12573 · HTML: https://mlsanity.com/paper/2208.12573/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression](https://mlsanity.com/paper/2005.07178/) (2020)
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [3D Point Cloud Processing and Learning for Autonomous Driving](https://mlsanity.com/paper/2003.00601/) (2020)
- [Transformer-based Image Compression](https://mlsanity.com/paper/2111.06707/) (2021)
- [VoxelContext-Net: An Octree based Framework for Point Cloud Compression](https://mlsanity.com/paper/2105.02158/) (2021)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Improved Deep Point Cloud Geometry Compression](https://mlsanity.com/paper/2006.09043/) (2020)
- [MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models](https://mlsanity.com/paper/2011.07590/) (2020)

## Built on by (most cited first, 6 of 6)

- [RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2503.12382/) (2025)
- [Geometric Prior Based Deep Human Point Cloud Geometry Compression](https://mlsanity.com/paper/2305.01309/) (2023)
- [TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation](https://mlsanity.com/paper/2310.02260/) (2023)
- [Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding](https://mlsanity.com/paper/2301.12165/) (2023)
- [Point Cloud Compression and Objective Quality Assessment: A Survey](https://mlsanity.com/paper/2506.22902/) (2025)
- [Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation](https://mlsanity.com/paper/2606.31609/) (2026)

## Abstract (arXiv)

Although convolutional representation of multiscale sparse tensor demonstrated its superior efficiency to accurately model the occupancy probability for the compression of geometry component of dense object point clouds, its capacity for representing sparse LiDAR point cloud geometry (PCG) was largely limited. This is because 1) fixed receptive field of the convolution cannot characterize extremely and unevenly distributed sparse LiDAR points very well; and 2) pretrained convolutions with fixed weights are insufficient to dynamically capture information conditioned on the input. This work therefore suggests the neighborhood point attention (NPA) to tackle them, where we first use k nearest neighbors (kNN) to construct adaptive local neighborhood; and then leverage the self-attention mechanism to dynamically aggregate information within this neighborhood. Such NPA is devised as a NPAFormer to best exploit cross-scale and same-scale correlations for geometric occupancy probability estimation. Compared with the anchor using standardized G-PCC, our method provides >17% BD-rate gains for lossy compression, and >14% bitrate reduction for lossless scenario using popular LiDAR point clouds in SemanticKITTI and Ford datasets. Compared with the state-of-the-art (SOTA) solution using attention optimized octree coding method, our approach requires much less decoding runtime with about 640 times speedup on average, while still presenting better compression efficiency.