TY - GEN
T1 - Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
AU - Spadaro, Gabriele
AU - Presta, Alberto
AU - Giraldo, Jhony H.
AU - Grangetto, Marco
AU - Hu, Wei
AU - Valenzise, Giuseppe
AU - Fiandrotti, Attilio
AU - Tartaglione, Enzo
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - 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.
AB - 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.
KW - Denoising Diffusion Probabilistic Models
KW - Geometry Point Cloud Compression
KW - Learnable Vector Quantizer
UR - https://www.scopus.com/pages/publications/105022644800
U2 - 10.1109/ICME59968.2025.11209228
DO - 10.1109/ICME59968.2025.11209228
M3 - Conference contribution
AN - SCOPUS:105022644800
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2025 IEEE International Conference on Multimedia and Expo
PB - IEEE Computer Society
T2 - 2025 IEEE International Conference on Multimedia and Expo, ICME 2025
Y2 - 30 June 2025 through 4 July 2025
ER -