# Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression

arXiv: https://arxiv.org/abs/2111.10633 · HTML: https://mlsanity.com/paper/2111.10633/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 20 Nov 2021.

## Builds on (most cited first, 21 of 21)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [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 3D convolutional neural networks](https://mlsanity.com/paper/1505.02890/) (2015)
- [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)
- [SBNet: Sparse Blocks Network for Fast Inference](https://mlsanity.com/paper/1801.02108/) (2018)
- [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)
- [Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds](https://mlsanity.com/paper/1905.03691/) (2019)
- [Multiscale deep context modeling for lossless point cloud geometry compression](https://mlsanity.com/paper/2104.09859/) (2021)
- [Lossless Coding of Point Cloud Geometry using a Deep Generative Model](https://mlsanity.com/paper/2107.00400/) (2021)
- [Neural Network Modeling of Probabilities for Coding the Octree Representation of Point Clouds](https://mlsanity.com/paper/2106.06482/) (2021)

## Built on by (most cited first, 30 of 70)

- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [Inter-Frame Compression for Dynamic Point Cloud Geometry Coding](https://mlsanity.com/paper/2207.12554/) (2022)
- [GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression](https://mlsanity.com/paper/2209.04401/) (2022)
- [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)
- [SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds](https://mlsanity.com/paper/2409.10293/) (2024)
- [HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder](https://mlsanity.com/paper/2505.01938/) (2025)
- [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)
- [ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression](https://mlsanity.com/paper/2211.10916/) (2022)
- [UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach](https://mlsanity.com/paper/2503.18541/) (2025)
- [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)
- [CARNet:Compression Artifact Reduction for Point Cloud Attribute](https://mlsanity.com/paper/2209.08276/) (2022)
- [Point Cloud Compression with Implicit Neural Representations: A Unified Framework](https://mlsanity.com/paper/2405.11493/) (2024)
- [Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding](https://mlsanity.com/paper/2301.12165/) (2023)
- [Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes](https://mlsanity.com/paper/2404.13550/) (2024)
- [Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss](https://mlsanity.com/paper/2407.08520/) (2024)
- [Deep Learning-based Compressed Domain Multimedia for Man and Machine: A Taxonomy and Application to Point Cloud Classification](https://mlsanity.com/paper/2310.18849/) (2023)
- [Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction](https://mlsanity.com/paper/2407.08528/) (2024)
- [Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement](https://mlsanity.com/paper/2408.02966/) (2024)
- [Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer](https://mlsanity.com/paper/2411.07899/) (2024)
- [PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport](https://mlsanity.com/paper/2503.00047/) (2025)
- [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)
- [Point Cloud Compression via Constrained Optimal Transport](https://mlsanity.com/paper/2403.08236/) (2024)
- [Towards Reproducible Learning-based Compression](https://mlsanity.com/paper/2410.09872/) (2024)
- [Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds](https://mlsanity.com/paper/2505.17442/) (2025)
- [Efficient and Generic Point Model for Lossless Point Cloud Attribute Compression](https://mlsanity.com/paper/2404.06936/) (2024)
- [Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimator](https://mlsanity.com/paper/2404.07698/) (2024)

## Abstract (arXiv)

This study develops a unified Point Cloud Geometry (PCG) compression method through the processing of multiscale sparse tensor-based voxelized PCG. We call this compression method SparsePCGC. The proposed SparsePCGC is a low complexity solution because it only performs the convolutions on sparsely-distributed Most-Probable Positively-Occupied Voxels (MP-POV). The multiscale representation also allows us to compress scale-wise MP-POVs by exploiting cross-scale and same-scale correlations extensively and flexibly. The overall compression efficiency highly depends on the accuracy of estimated occupancy probability for each MP-POV. Thus, we first design the Sparse Convolution-based Neural Network (SparseCNN) which stacks sparse convolutions and voxel sampling to best characterize and embed spatial correlations. We then develop the SparseCNN-based Occupancy Probability Approximation (SOPA) model to estimate the occupancy probability either in a single-stage manner only using the cross-scale correlation, or in a multi-stage manner by exploiting stage-wise correlation among same-scale neighbors. Besides, we also suggest the SparseCNN based Local Neighborhood Embedding (SLNE) to aggregate local variations as spatial priors in feature attribute to improve the SOPA. Our unified approach not only shows state-of-the-art performance in both lossless and lossy compression modes across a variety of datasets including the dense object PCGs (8iVFB, Owlii, MUVB) and sparse LiDAR PCGs (KITTI, Ford) when compared with standardized MPEG G-PCC and other prevalent learning-based schemes, but also has low complexity which is attractive to practical applications.