Research map / Point clouds / Point cloud classification
CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating
Read the paperCheck 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 CPCGAN instead of tree-GAN | 3D point-cloud generation · Chair | COV-EMD: 33.92 -> 50.41 | Helped |
| Use CPCGAN instead of tree-GAN | 3D point-cloud generation · Airplane | MMD-EMD: 0.0584 -> 0.0417 | Helped |
| Use CPCGAN instead of tree-GAN | semantic-label generation · Chair | mIoUNL: 85.342 -> 89.814 | Helped |
| Use CPCGAN instead of tree-GAN | semantic-label generation · Airplane | mAccNL: 79.072 -> 92.355 | Helped |
| Add Delta point breeding to the variant without Delta, attention, or average-pooling (ablation) | CPCGAN · Chair | mIoU: 24.781 -> 69.730 | Helped |
| Add Delta point breeding to the variant without Delta, attention, or average-pooling (ablation) | CPCGAN · Chair | FPD: 1.240 -> 1.188 | Helped |
| Add Delta point breeding to the variant without Delta, attention, or average-pooling (ablation) | CPCGAN · Airplane | FPD: 0.537 -> 0.617 | Hurt |
| Add self-attention to the Delta variant (ablation) | CPCGAN · Airplane | mIoU: 59.407 -> 59.747 | Helped |
| Add self-attention to the Delta variant (ablation) | CPCGAN · Airplane | FPD: 0.617 -> 0.696 | Hurt |
| Replace max-pooling with global average-pooling in the Structure GAN discriminator (ablation) | CPCGAN · Chair | mIoU: 75.332 -> 59.003 | Hurt |
| Replace max-pooling with global average-pooling in the Structure GAN discriminator (ablation) | CPCGAN · Chair | fwIoU: 73.609 -> 76.269 | Helped |
| Replace max-pooling with global average-pooling in the Structure GAN discriminator (ablation) | CPCGAN · Airplane | FPD: 0.696 -> 0.522 | Helped |
Closest papers by meaning
- Learning Representations and Generative Models for 3D Point Clouds (ICML 2018 · similarity 0.87)
- Learning Progressive Point Embeddings for 3D Point Cloud Generation (CVPR 2021 · similarity 0.87)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 2025 · similarity 0.87)
- LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks (CVPR 2020 · similarity 0.86)
- Learning Localized Generative Models for 3D Point Clouds via Graph Convolution (ICLR 2019 · similarity 0.86)
- Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification (CVPR 2021 · similarity 0.86)
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.