Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Point Cloud Compression via Constrained Optimal Transport (2403.08236v1)

Published 13 Mar 2024 in cs.CV and eess.IV

Abstract: 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 \url{https://github.com/cognaclee/PCC-COT}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. “An overview of ongoing point cloud compression standardization activities: Video-based (v-pcc) and geometry-based (g-pcc),” APSIPA Trans. Signal Inf. Process., vol. 9, 2020.
  2. “A novel grid-based geometry compression framework for spinning lidar point clouds,” in ICME. IEEE, 2022, pp. 1–6.
  3. “Octsqueeze: Octree-structured entropy model for lidar compression,” in CVPR, 2020, pp. 1313–1323.
  4. “Learning convolutional transforms for lossy point cloud geometry compression,” in ICIP. IEEE, 2019, pp. 4320–4324.
  5. “Lossy point cloud geometry compression via end-to-end learning,” TCSVT, vol. 31, pp. 4909–4923, 2021.
  6. “Improved deep point cloud geometry compression,” in MMSP. IEEE, 2020, pp. 1–6.
  7. “Sparse tensor-based multiscale representation for point cloud geometry compression,” TPAMI, 2022.
  8. “Efficient hierarchical entropy model for learned point cloud compression,” in CVPR, 2023, pp. 14368–14377.
  9. “Pchm-net: A new point cloud compression framework for both human vision and machine vision,” in ICME. IEEE, 2023, pp. 1997–2002.
  10. “3d point cloud geometry compression on deep learning,” in Proceedings of the 27th ACM MM, 2019, pp. 890–898.
  11. “Deep autoencoder-based lossy geometry compression for point clouds,” arXiv preprint:1905.03691, 2019.
  12. “3d point cloud attribute compression via graph prediction,” IEEE SPL, vol. 27, pp. 176–180, 2020.
  13. “Deep compression for dense point cloud maps,” Robot. Autom. Lett., vol. 6, pp. 2060–2067, 2021.
  14. “Multiscale point cloud geometry compression,” in DCC. IEEE, 2021, pp. 73–82.
  15. “Density-preserving deep point cloud compression,” in CVPR, 2022, pp. 333–342.
  16. “Point cloud compression based on joint optimization of graph transform and entropy coding for efficient data broadcasting,” IEEE Trans. Broadcast., 2023.
  17. “Voxelcontext-net: An octree based framework for point cloud compression,” in CVPR, 2021, pp. 6042–6051.
  18. Y. Blau and T. Michaeli, “Rethinking lossy compression: The rate-distortion-perception tradeoff,” in ICML, 2019, pp. 675–685.
  19. “On perceptual lossy compression: The cost of perceptual reconstruction and an optimal training framework,” in ICML, 2021, pp. 11682–11692.
  20. “Universal rate-distortion-perception representations for lossy compression,” NeurIPS, vol. 34, pp. 11517–11529, 2021.
  21. “Compression of 3d point clouds using a region-adaptive hierarchical transform,” TIP, vol. 25, no. 8, pp. 3947–3956, 2016.
  22. “Muscle: Multi sweep compression of lidar using deep entropy models,” NeurIPS, vol. 33, pp. 22170–22181, 2020.
  23. “Adaptive deep learning-based point cloud geometry coding,” J Sel Top Signal Process, vol. 15, pp. 415–430, 2020.
  24. Elements of information theory, Wiley-Interscience, 2006.
  25. Claude E Shannon et al., “Coding theorems for a discrete source with a fidelity criterion,” IRE Nat. Conv. Rec, vol. 4, no. 142-163, pp. 1, 1959.
  26. “End-to-end optimized image compression,” arXiv preprint arXiv:1611.01704, 2016.
  27. “Lossy compression with distribution shift as entropy constrained optimal transport,” in ICLR, 2021.
  28. “Lossy geometry compression of 3d point cloud data via an adaptive octree-guided network,” in ICME. IEEE, 2020, pp. 1–6.
  29. “Computational optimal transport: With applications to data science,” Found. Trends Mach. Learn., pp. 355–607, 2019.
  30. “Weakly supervised point cloud upsampling via optimal transport,” in ICASSP 2022-2022. IEEE, 2022, pp. 2564–2568.
  31. Gaspard Monge, “Mémoire sur la théorie des déblais et des remblais,” Histoire de l’Académie Royale des Sciences de Paris, 1781.
  32. “A geometric view of optimal transportation and generative model,” CAGD, vol. 68, pp. 1–21, 2019.
  33. “Pu-gan: a point cloud upsampling adversarial network,” in ICCV, 2019, pp. 73–82.
  34. “The unreasonable effectiveness of deep features as a perceptual metric,” in CVPR, 2018, pp. 586–595.
  35. “Wasserstein gan with quadratic transport cost,” in ICCV, 2019, pp. 4832–4841.
  36. “Samplenet: Differentiable point cloud sampling,” in CVPR, 2020, pp. 7578–7588.
  37. “Point transformer,” in ICCV, 2021, pp. 16259–16268.
  38. “Dynamic graph cnn for learning on point clouds,” ACM TOG, vol. 38, no. 5, pp. 1–12, 2019.
  39. “Semantickitti: A dataset for semantic scene understanding of lidar sequences,” in ICCV, 2019, pp. 9297–9307.
  40. “Shapenet: An information-rich 3d model repository,” arXiv preprint arXiv:1512.03012, 2015.
  41. “Mpeg pcc dataset,” Accessed: 2022.
  42. “Google/draco: a library for compressing and decompressing 3d geometric meshes and point clouds,” 2018.
  43. “Design, implementation, and evaluation of a point cloud codec for tele-immersive video,” TCSVT, vol. 27, no. 4, pp. 828–842, 2016.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now