Research map / Point clouds / Point cloud classification
Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
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 Generative PointNet instead of PointFlow for reconstruction | ModelNet10 · night stand and sofa reconstruction | CD for night stand; EMD for sofa: 0.464 -> 0.378; 0.888 -> 0.703 | Helped |
| Use Generative PointNet instead of PointFlow for reconstruction | ModelNet10 bathtub · bathtub reconstruction | CD: 0.289 -> 0.321 | Hurt |
| Use Generative PointNet instead of PointFlow for synthesis | ModelNet10 · night stand synthesis | JSD: 0.240 -> 0.590 | Hurt |
| Use Generative PointNet instead of PointFlow for synthesis | ModelNet10 · night stand and toilet synthesis | MMD-CD: 0.888 -> 0.692; 0.965 -> 0.816 | Helped |
| Use Generative PointNet instead of PointFlow for synthesis | ModelNet10 · chair and desk synthesis | Coverage: 42.00 -> 56.00; 46.51 -> 52.33 | Helped |
| Train a classifier using the learned point-cloud representation | ModelNet10 · test classification | accuracy: 95.4% -> 93.7% | Hurt |
| Delete 94% of points from each test point cloud | Generative PointNet classifier · ModelNet10 test classification | accuracy: 90.20% | Hurt |
| Retain only 20 points in each test point cloud | Generative PointNet classifier · ModelNet10 test classification | accuracy: 53.19% | Hurt |
Closest papers by meaning
- Learning Progressive Point Embeddings for 3D Point Cloud Generation (CVPR 2021 · similarity 0.91)
- Learning Representations and Generative Models for 3D Point Clouds (ICML 2018 · similarity 0.88)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.88)
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (NeurIPS 2017 · similarity 0.88)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.88)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 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.