Scalable Human-Machine Point Cloud Compression
Not on the map. Why?
Abstract (arXiv)
Due to the limited computational capabilities of edge devices, deep learning inference can be quite expensive. One remedy is to compress and transmit point cloud data over the network for server-side processing. Unfortunately, this approach can be sensitive to network factors, including available bitrate. Luckily, the bitrate requirements can be reduced without sacrificing inference accuracy by using a machine task-specialized codec. In this paper, we present a scalable codec for point-cloud data that is specialized for the machine task of classification, while also providing a mechanism for human viewing. In the proposed scalable codec, the "base" bitstream supports the machine task, and an "enhancement" bitstream may be used for better input reconstruction performance for human viewing. We base our architecture on PointNet++, and test its efficacy on the ModelNet40 dataset. We show significant improvements over prior non-specialized codecs.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 19 Feb 2024.
Builds on
18 of 28 references.
References · 18
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2018Variational image compression with a scale hyperpriorcited by 935
- 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
- 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 276
- 2020Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analyticscited by 80
- 2021Scalable Image Coding for Humans and Machinescited by 66
- 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
- 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
- 2021Image coding for machines: an end-to-end learned approachcited by 47
- 2022Density-preserving Deep Point Cloud Compressioncited by 39
- 2020Towards Coding for Human and Machine Vision: A Scalable Image Coding Approachcited by 31
6 more
- 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
- 2021Collaborative Intelligence: Challenges and Opportunitiescited by 19
- 2022Collaborative Inference for AI-Empowered IoT Devicescited by 15
- 2022IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compressioncited by 8
- 2023Base Layer Efficiency in Scalable Human-Machine Codingcited by 4
- 2023Learned Point Cloud Compression for Classificationcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.