Research map / Point clouds / Point cloud classification
Accelerated Generative Models for 3D Point Cloud Data
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use hierarchical GMM construction instead of a flat GMM | GMM construction on Burghers · Burghers, #J=8 | E step execution time: 79.2 ms vs 61.6 ms; 0.78× | Hurt |
| Use hierarchical GMM construction instead of a flat GMM | GMM construction on Burghers · Burghers, #J=64 | E step execution time: 145.6 ms vs 166.5 ms; 1.14× | Helped |
| Use hierarchical GMM construction instead of a flat GMM | GMM construction on Burghers · Burghers, #J=512 | E step execution time: 184.2 ms vs 1145.4 ms; 6.22× | Helped |
| Use hierarchical GMM construction instead of a flat GMM | GMM construction on Burghers · Burghers, #J=4096 | E step execution time: 213.8 ms vs 8750.8 ms; 40.93× | Helped |
| Use hierarchical GMM construction instead of a flat GMM | GMM construction on Burghers · Burghers, #J=32768 | E step execution time: 251.0 ms vs 71061.7 ms; 283.11× | Helped |
| Increase the hierarchy from L2 to L3 | Hierarchical GMM · Stanford Bunny | PSNR: 45.7 -> 48.7 | Helped |
| Increase the hierarchy from L3 to L4 | Hierarchical GMM · Stanford Bunny | PSNR: 48.7 -> 50.7 | Helped |
| Use hierarchical GMM rather than 3D-NDT, 3D-NDT-Octree, or subsampling at comparable model sizes | Point-cloud representation · Burghers, Lounge, and Cactus | PSNR | Helped |
| Use hierarchical GMM rather than 3D-NDT-Octree at higher model sizes | Point-cloud representation · Stanford Bunny | PSNR | Mixed |
Closest papers by meaning
- PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction (CVPR 2026 · similarity 0.89)
- Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion (AAAI 2025 · similarity 0.88)
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · similarity 0.88)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.87)
- PointInfinity: Resolution-Invariant Point Diffusion Models (CVPR 2024 · similarity 0.87)
- Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.