Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
This addresses bandwidth-constrained applications like VR/AR by enabling better compression with fewer bits, though it is an incremental improvement over existing diffusion-based techniques.
The paper tackles efficient point cloud compression at low bit-rates by proposing a Denoising Diffusion Probabilistic Model (DDPM-PCC) architecture, achieving improved rate-distortion performance on ShapeNet and ModelNet40 datasets compared to existing methods.
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.