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

TL;DR

This paper introduces a novel diffusion-based model for compressing point clouds at low bit-rates, achieving better rate-distortion performance than existing methods by combining a PointNet encoder with a learnable quantizer.

Contribution

It presents a new DDPM architecture for low-bit-rate point cloud compression, integrating a PointNet encoder and learnable quantization for improved efficiency.

Findings

Outperforms state-of-the-art methods at low bit-rates

Achieves better rate-distortion trade-offs on ShapeNet and ModelNet40

Code is publicly available for reproducibility

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.