English

Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates

Computer Vision and Pattern Recognition 2025-05-20 v1 Artificial Intelligence Machine Learning

Abstract

Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, requiring many bits for compression. This paper proposes a "Denoising Diffusion Probabilistic Model" (DDPM) architecture for point cloud compression (DDPM-PCC) at low bit-rates. A PointNet encoder produces the condition vector for the generation, which is then quantized via a learnable vector quantizer. This configuration allows to achieve a low bitrates while preserving quality. Experiments on ShapeNet and ModelNet40 show improved rate-distortion at low rates compared to standardized and state-of-the-art approaches. We publicly released the code at https://github.com/EIDOSLAB/DDPM-PCC.

Keywords

Cite

@article{arxiv.2505.13316,
  title  = {Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates},
  author = {Gabriele Spadaro and Alberto Presta and Jhony H. Giraldo and Marco Grangetto and Wei Hu and Giuseppe Valenzise and Attilio Fiandrotti and Enzo Tartaglione},
  journal= {arXiv preprint arXiv:2505.13316},
  year   = {2025}
}

Comments

6 pages, 5 figures, accepted at ICME 2025

R2 v1 2026-07-01T02:22:23.345Z