Research map / Point clouds / Shape and surface completion
Learning Progressive Point Embeddings for 3D Point Cloud Generation
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 the dual-generator method instead of PDGN | Point cloud generation · ShapeNet chair | JSD: 0.0827 -> 0.0716 | Helped |
| Use the dual-generator method instead of PDGN | Point cloud generation · ShapeNet car | JSD: 0.0607 -> 0.0531 | Helped |
| Use the dual-generator method instead of PDGN | Point cloud generation · ShapeNet airplane | MMD-EMD: 0.1211 -> 0.0646 | Helped |
| Add the second generator to the first generator with oversampling (ablation) | Progressive point cloud generator · ShapeNet chair | JSD: 0.0776 -> 0.0716 | Helped |
| Add the oversampling layer to the first generator (ablation) | Progressive point cloud generator · ShapeNet chair | JSD: 0.0812 -> 0.0776 | Helped |
| Add the second generator to the first generator with oversampling (ablation) | Progressive point cloud generator · ShapeNet car | JSD: 0.0592 -> 0.0531 | Helped |
| Add the oversampling layer to the first generator (ablation) | Progressive point cloud generator · ShapeNet car | JSD: 0.0621 -> 0.0592 | Helped |
| Add the second generator to the first generator with oversampling (ablation) | Progressive point cloud generator · ShapeNet airplane | JSD: 0.0817 -> 0.0719 | Helped |
| Add the oversampling layer to the first generator (ablation) | Progressive point cloud generator · ShapeNet airplane | JSD: 0.0845 -> 0.0817 | Helped |
| Use an MLP-plus-set-abstraction discriminator rather than MLP-only raw-GAN discriminator (ablation) | GAN point-cloud discriminator · ShapeNet object categories | point distribution uniformity | Helped |
Closest papers by meaning
- Learning Representations and Generative Models for 3D Point Clouds (ICML 2018 · similarity 0.91)
- Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification (CVPR 2021 · similarity 0.91)
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction (AAAI 2018 · similarity 0.90)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 2025 · similarity 0.88)
- Point Cloud Pre-training with Diffusion Models (CVPR 2024 · similarity 0.87)
- GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors (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.