mlsanityData to 7 Oct 2026

Point Cloud Compression via Constrained Optimal Transport

arXiv 2403.08236 ↗First posted 13 Mar 2024cs.CV eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel point cloud compression method COT-PCC by formulating the task as a constrained optimal transport (COT) problem. COT-PCC takes the bitrate of compressed features as an extra constraint of optimal transport (OT) which learns the distribution transformation between original and reconstructed points. Specifically, the formulated COT is implemented with a generative adversarial network (GAN) and a bitrate loss for training. The discriminator measures the Wasserstein distance between input and reconstructed points, and a generator calculates the optimal mapping between distributions of input and reconstructed point cloud. Moreover, we introduce a learnable sampling module for downsampling in the compression procedure. Extensive results on both sparse and dense point cloud datasets demonstrate that COT-PCC outperforms state-of-the-art methods in terms of both CD and PSNR metrics. Source codes are available at urlhttps://github.com/cognaclee/PCC-COT.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

22 of 45 references.

References · 22

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2020Point Transformercited by 1,462
  5. 2018Computational Optimal Transportcited by 765
  6. 2016End-to-end Optimized Image Compressioncited by 673
  7. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  8. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  9. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  10. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 72
  11. 2020Multiscale Point Cloud Geometry Compressioncited by 72
  12. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 69
10 more
  1. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 60
  2. 2019Learned Point Cloud Geometry Compressioncited by 58
  3. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  4. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46
  5. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  6. 2020MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Modelscited by 42
  7. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  8. 2017A Geometric View of Optimal Transportation and Generative Modelcited by 31
  9. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  10. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27

Built on by

Cited by year

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

3 papers.

  1. 2025Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Cloudscited by 3
  2. 2024DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Cloudscited by 1
  3. 2025Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Ratescited by 0