mlsanityData to 7 Oct 2026

Improved Deep Point Cloud Geometry Compression

arXiv 2006.09043 ↗First posted 16 Jun 2020cs.CV cs.LG eess.IVcited by 43

Not on the map. Why?

Abstract (arXiv)

Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In addition, we present an extensive ablation study on the impact of each of these factors, in order to provide a better understanding about why they improve RD performance. An optimal combination of the proposed improvements achieves BD-PSNR gains over G-PCC trisoup and octree of 5.50 (6.48) dB and 6.84 (5.95) dB, respectively, when using the point-to-point (point-to-plane) metric. Code is available at https://github.com/mauriceqch/pcc_geo_cnn_v2 .

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 13; 2023: 6; 2024: 7; 2025: 10; 2026: 1.

43 papers.

Sort:

By area:

  1. 2022An Introduction to Neural Data Compressioncited by 78
  2. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 69
  3. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  4. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 57
  5. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  6. 2023Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Modelcited by 25
  7. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  8. 2022Inter-Frame Compression for Dynamic Point Cloud Geometry Codingcited by 21
  9. 2021LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networkscited by 19
  10. 2022GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compressioncited by 17
  11. 2021Patch-Based Deep Autoencoder for Point Cloud Geometry Compressioncited by 14
  12. 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streamingcited by 11
31 more
  1. 2021Lossless Coding of Point Cloud Geometry using a Deep Generative Modelcited by 10
  2. 2022Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compressioncited by 9
  3. 2024The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machinecited by 9
  4. 2022IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compressioncited by 8
  5. 2022ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compressioncited by 8
  6. 2023Geometric Prior Based Deep Human Point Cloud Geometry Compressioncited by 8
  7. 2025UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approachcited by 8
  8. 2024PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compressioncited by 7
  9. 2022Efficient LiDAR Point Cloud Geometry Compression Through Neighborhood Point Attentioncited by 6
  10. 2022Deep Geometry Post-Processing for Decompressed Point Cloudscited by 5
  11. 2024Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compressioncited by 5
  12. 2022Variable Rate Compression for Raw 3D Point Cloudscited by 4
  13. 2023Deep Learning-based Compressed Domain Multimedia for Man and Machine: A Taxonomy and Application to Point Cloud Classificationcited by 4
  14. 2025Voxel-based Point Cloud Geometry Compression with Space-to-Channel Contextcited by 4
  15. 2025ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Visioncited by 4
  16. 2023Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attentioncited by 3
  17. 2024Point Cloud Compression via Constrained Optimal Transportcited by 3
  18. 20224DAC: Learning Attribute Compression for Dynamic Point Cloudscited by 2
  19. 2023Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compressioncited by 2
  20. 2024Point Cloud Geometry Scalable Coding with a Quality-Conditioned Latents Probability Estimatorcited by 2
  21. 2024Full reference point cloud quality assessment using support vector regressioncited by 2
  22. 2024Learned Compression of Point Cloud Geometry and Attributes in a Single Model through Multimodal Rate-Controlcited by 1
  23. 2025Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Spacecited by 1
  24. 2025Point Cloud Compression and Objective Quality Assessment: A Surveycited by 1
  25. 2021A deep perceptual metric for 3D point cloudscited by 0
  26. 2021DeepCompress: Efficient Point Cloud Geometry Compressioncited by 0
  27. 2025Point Cloud Geometry Scalable Coding Using a Resolution and Quality-conditioned Latents Probability Estimatorcited by 0
  28. 2025VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distributioncited by 0
  29. 2025Unified Geometry and Color Compression Framework for Point Clouds via Generative Diffusion Priorscited by 0
  30. 2025Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Ratescited by 0
  31. 2026SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representationcited by 0