A diffusion model conditioned on a vector-quantized PointNet latent reconstructs point clouds at 0.06-0.25 bits per point with better reported quality than G-PCC, Draco, D-PCC, and COT-PCC on ShapeNet and ModelNet40.
An overview of ongoing point cloud compression standardization activities: video-based (v-pcc) and geometry-based (g- pcc),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
A diffusion model conditioned on a vector-quantized PointNet latent reconstructs point clouds at 0.06-0.25 bits per point with better reported quality than G-PCC, Draco, D-PCC, and COT-PCC on ShapeNet and ModelNet40.