mlsanityData to 14 Oct 2026

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

arXiv 2208.02519 ↗First posted 4 Aug 2022cs.CV cs.IT cs.MMcited by 8

Not on the map. Why?

Abstract (arXiv)

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc. With the boost of the number of points in the data, how to efficiently compress point cloud becomes a challenging problem. In this paper, we propose a set of significant improvements to patch-based point cloud compression, i.e., a learnable context model for entropy coding, octree coding for sampling centroid points, and an integrated compression and training process. In addition, we propose an adversarial network to improve the uniformity of points during reconstruction. Our experiments show that the improved patch-based autoencoder outperforms the state-of-the-art in terms of rate-distortion performance, on both sparse and large-scale point clouds. More importantly, our method can maintain a short compression time while ensuring the reconstruction quality.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 4 Aug 2022.

Builds on

20 of 34 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  6. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  7. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  8. 2018Practical Full Resolution Learned Lossless Image Compressioncited by 94
  9. 2020Multiscale Point Cloud Geometry Compressioncited by 74
  10. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 73
  11. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
  12. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
8 more
  1. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  2. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  3. 2020Learning Better Lossless Compression Using Lossy Compressioncited by 33
  4. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  5. 2019Learning Image and Video Compression through Spatial-Temporal Energy Compactioncited by 27
  6. 2018Deep Generative Video Compressioncited by 23
  7. 2021SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Renderingcited by 17
  8. 2021Patch-Based Deep Autoencoder for Point Cloud Geometry Compressioncited by 15

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 2.

8 papers.

  1. 2024Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenescited by 5
  2. 2024Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinementcited by 4
  3. 2023Learned Point Cloud Compression for Classificationcited by 3
  4. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Cloudscited by 2
  5. 2024Scalable Human-Machine Point Cloud Compressioncited by 1
  6. 2024Att2CPC: Attention-Guided Lossy Attribute Compression of Point Cloudscited by 1
  7. 2025UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Cloudscited by 1
  8. 2025PVINet: Point-Voxel Interlaced Network for Point Cloud Compressioncited by 0