# Re-Densification Meets Cross-Scale Propagation: Real-Time Neural Compression of LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2508.20466 · HTML: https://mlsanity.com/paper/2508.20466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression](https://mlsanity.com/paper/2005.07178/) (2020)
- [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)
- [Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression](https://mlsanity.com/paper/1903.08548/) (2019)
- [MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models](https://mlsanity.com/paper/2011.07590/) (2020)
- [Density-preserving Deep Point Cloud Compression](https://mlsanity.com/paper/2204.12684/) (2022)
- [TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs](https://mlsanity.com/paper/2311.12862/) (2023)
- [RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding](https://mlsanity.com/paper/2206.01738/) (2022)
- [Deep Point Cloud Reconstruction](https://mlsanity.com/paper/2111.11704/) (2021)
- [SCP: Spherical-Coordinate-based Learned Point Cloud Compression](https://mlsanity.com/paper/2308.12535/) (2023)
- [RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2503.12382/) (2025)
- [Lossless Coding of Point Cloud Geometry using a Deep Generative Model](https://mlsanity.com/paper/2107.00400/) (2021)
- [Point Cloud Compression with Sibling Context and Surface Priors](https://mlsanity.com/paper/2205.00760/) (2022)
- [R-PCC: A Baseline for Range Image-based Point Cloud Compression](https://mlsanity.com/paper/2109.07717/) (2021)
- [Learning-based Lossless Point Cloud Geometry Coding using Sparse Tensors](https://mlsanity.com/paper/2204.05043/) (2022)
- [PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression](https://mlsanity.com/paper/2402.07243/) (2024)
- [RecNet: An Invertible Point Cloud Encoding through Range Image Embeddings for Multi-Robot Map Sharing and Reconstruction](https://mlsanity.com/paper/2402.02192/) (2024)
- [Real-Time LiDAR Point Cloud Compression and Transmission for Resource-constrained Robots](https://mlsanity.com/paper/2502.06123/) (2025)

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

- [AnyPcc: Compressing Any Point Cloud with a Single Universal Model](https://mlsanity.com/paper/2510.20331/) (2025)
- [PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression](https://mlsanity.com/paper/2605.01320/) (2026)

## Abstract (arXiv)

LiDAR point clouds are fundamental to various applications, yet high-precision scans incur substantial storage and transmission overhead. Existing methods typically convert unordered points into hierarchical octree or voxel structures for dense-to-sparse predictive coding. However, the extreme sparsity of geometric details hinders efficient context modeling, thereby limiting their compression performance and speed. To address this challenge, we propose to generate compact features for efficient predictive coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module re-densifies encoded sparse geometry, extracts features at denser scale, and then re-sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation. This design facilitates information sharing across scales, thereby reducing redundant feature extraction and providing enriched features for the Geometry Re-Densification Module. By integrating these two modules, our method yields a compact feature representation that provides efficient context modeling and accelerates the coding process. Experiments on the KITTI dataset demonstrate state-of-the-art compression ratios and real-time performance, achieving 26 FPS for encoding/decoding at 12-bit quantization. Code is available at https://github.com/pengpeng-yu/FastPCC.