# Learned Point Cloud Geometry Compression

arXiv: https://arxiv.org/abs/1909.12037 · HTML: https://mlsanity.com/paper/1909.12037/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 30 of 58)

- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Density-preserving Deep Point Cloud Compression](https://mlsanity.com/paper/2204.12684/) (2022)
- [Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline](https://mlsanity.com/paper/2209.12028/) (2022)
- [Inter-Frame Compression for Dynamic Point Cloud Geometry Coding](https://mlsanity.com/paper/2207.12554/) (2022)
- [Dense Pixel-to-Pixel Harmonization via Continuous Image Representation](https://mlsanity.com/paper/2303.01681/) (2023)
- [Compact Neural Graphics Primitives with Learned Hash Probing](https://mlsanity.com/paper/2312.17241/) (2023)
- [D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction](https://mlsanity.com/paper/2205.01135/) (2022)
- [GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression](https://mlsanity.com/paper/2209.04401/) (2022)
- [Patch-Based Deep Autoencoder for Point Cloud Geometry Compression](https://mlsanity.com/paper/2110.09109/) (2021)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming](https://mlsanity.com/paper/2509.17513/) (2025)
- [Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression](https://mlsanity.com/paper/2209.12512/) (2022)
- [Geometric Prior Based Deep Human Point Cloud Geometry Compression](https://mlsanity.com/paper/2305.01309/) (2023)
- [The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine](https://mlsanity.com/paper/2409.08130/) (2024)
- [PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression](https://mlsanity.com/paper/2402.07243/) (2024)
- [Efficient LiDAR Point Cloud Geometry Compression Through Neighborhood Point Attention](https://mlsanity.com/paper/2208.12573/) (2022)
- [Point Cloud Compression with Implicit Neural Representations: A Unified Framework](https://mlsanity.com/paper/2405.11493/) (2024)
- [Deep Geometry Post-Processing for Decompressed Point Clouds](https://mlsanity.com/paper/2204.13952/) (2022)
- [Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding](https://mlsanity.com/paper/2301.12165/) (2023)
- [Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching](https://mlsanity.com/paper/2305.05356/) (2023)
- [Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression](https://mlsanity.com/paper/2402.11250/) (2024)
- [MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network](https://mlsanity.com/paper/2406.16633/) (2024)
- [Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss](https://mlsanity.com/paper/2407.08520/) (2024)
- [Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor](https://mlsanity.com/paper/2406.00791/) (2024)
- [Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement](https://mlsanity.com/paper/2408.02966/) (2024)
- [Voxel-based Point Cloud Geometry Compression with Space-to-Channel Context](https://mlsanity.com/paper/2503.18283/) (2025)
- [ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision](https://mlsanity.com/paper/2504.14240/) (2025)
- [Learning Neural Volumetric Field for Point Cloud Geometry Compression](https://mlsanity.com/paper/2212.05589/) (2022)
- [Point Cloud Compression via Constrained Optimal Transport](https://mlsanity.com/paper/2403.08236/) (2024)

## Abstract (arXiv)

This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a.k.a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE). In our approach, PCG is first voxelized, scaled and partitioned into non-overlapped 3D cubes, which is then fed into stacked 3D convolutions for compact latent feature and hyperprior generation. Hyperpriors are used to improve the conditional probability modeling of latent features. A weighted binary cross-entropy (WBCE) loss is applied in training while an adaptive thresholding is used in inference to remove unnecessary voxels and reduce the distortion. Objectively, our method exceeds the geometry-based point cloud compression (G-PCC) algorithm standardized by well-known Moving Picture Experts Group (MPEG) with a significant performance margin, e.g., at least 60% BD-Rate (Bjontegaard Delta Rate) gains, using common test datasets. Subjectively, our method has presented better visual quality with smoother surface reconstruction and appealing details, in comparison to all existing MPEG standard compliant PCC methods. Our method requires about 2.5MB parameters in total, which is a fairly small size for practical implementation, even on embedded platform. Additional ablation studies analyze a variety of aspects (e.g., cube size, kernels, etc) to explore the application potentials of our learned-PCGC.