# Lossless Coding of Point Cloud Geometry using a Deep Generative Model

arXiv: https://arxiv.org/abs/2107.00400 · HTML: https://mlsanity.com/paper/2107.00400/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [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)
- [3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation](https://mlsanity.com/paper/2002.10893/) (2020)
- [Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression](https://mlsanity.com/paper/1903.08548/) (2019)
- [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)
- [Generative Image Modeling Using Spatial LSTMs](https://mlsanity.com/paper/1506.03478/) (2015)
- [Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds](https://mlsanity.com/paper/1905.03691/) (2019)
- [Comments on "Compression of 3D Point Clouds Using a Region-Adaptive Hierarchical Transform"](https://mlsanity.com/paper/1805.09146/) (2018)

## Built on by (most cited first, 10 of 10)

- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression](https://mlsanity.com/paper/2211.10916/) (2022)
- [LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression](https://mlsanity.com/paper/2408.08682/) (2024)
- [Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds](https://mlsanity.com/paper/2508.20466/) (2025)
- [DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression](https://mlsanity.com/paper/2601.12261/) (2026)
- [Towards Practical Lossless Neural Compression for LiDAR Point Clouds](https://mlsanity.com/paper/2603.25260/) (2026)
- [Streaming Lossless Volumetric Compression of Medical Images Using Gated Recurrent Convolutional Neural Network](https://mlsanity.com/paper/2311.16200/) (2023)

## Abstract (arXiv)

This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy. First, to take into account the PC sparsity, our method adaptively partitions a point cloud into multiple voxel block sizes. This partitioning is signalled via an octree. Second, we employ a deep auto-regressive generative model to estimate the occupancy probability of each voxel given the previously encoded ones. We then employ the estimated probabilities to code efficiently a block using a context-based arithmetic coder. Our context has variable size and can expand beyond the current block to learn more accurate probabilities. We also consider using data augmentation techniques to increase the generalization capability of the learned probability models, in particular in the presence of noise and lower-density point clouds. Experimental evaluation, performed on a variety of point clouds from four different datasets and with diverse characteristics, demonstrates that our method reduces significantly (by up to 30%) the rate for lossless coding compared to the state-of-the-art MPEG codec.