# Learned Point Cloud Compression for Classification

arXiv: https://arxiv.org/abs/2308.05959 · HTML: https://mlsanity.com/paper/2308.05959/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 11 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (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 Coding for Human and Machine Vision: A Scalable Image Coding Approach](https://mlsanity.com/paper/2001.02915/) (2020)
- [Supervised Compression for Resource-Constrained Edge Computing Systems](https://mlsanity.com/paper/2108.11898/) (2021)
- [End-to-end optimized image compression for machines, a study](https://mlsanity.com/paper/2011.06409/) (2020)
- [Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds](https://mlsanity.com/paper/1905.03691/) (2019)
- [Near-Lossless Deep Feature Compression for Collaborative Intelligence](https://mlsanity.com/paper/1804.09963/) (2018)
- [GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression](https://mlsanity.com/paper/2209.04401/) (2022)
- [Collaborative Inference for AI-Empowered IoT Devices](https://mlsanity.com/paper/2207.11664/) (2022)
- [IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression](https://mlsanity.com/paper/2208.02519/) (2022)
- [Efficient Feature Compression for Edge-Cloud Systems](https://mlsanity.com/paper/2211.09897/) (2022)

## Built on by (most cited first, 3 of 3)

- [The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine](https://mlsanity.com/paper/2409.08130/) (2024)
- [ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision](https://mlsanity.com/paper/2504.14240/) (2025)
- [Scalable Human-Machine Point Cloud Compression](https://mlsanity.com/paper/2402.12532/) (2024)

## Abstract (arXiv)

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited computational capabilities of end devices thus necessitate a codec for transmitting point cloud data over the network for server-side processing. Such a codec must be lightweight and capable of achieving high compression ratios without sacrificing accuracy. Motivated by this, we present a novel point cloud codec that is highly specialized for the machine task of classification. Our codec, based on PointNet, achieves a significantly better rate-accuracy trade-off in comparison to alternative methods. In particular, it achieves a 94% reduction in BD-bitrate over non-specialized codecs on the ModelNet40 dataset. For low-resource end devices, we also propose two lightweight configurations of our encoder that achieve similar BD-bitrate reductions of 93% and 92% with 3% and 5% drops in top-1 accuracy, while consuming only 0.470 and 0.048 encoder-side kMACs/point, respectively. Our codec demonstrates the potential of specialized codecs for machine analysis of point clouds, and provides a basis for extension to more complex tasks and datasets in the future.