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

2025/05/19 by Spadaro, Gabriele, Presta, Alberto, Giraldo, Jhony H. +5
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2505.13316

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.

Related

• Diff-PCC: Diffusion-based Neural Compression for 3D Point Clouds
• DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction
• DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds
• PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration
• A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling