Research map / Point clouds / Shape and surface completion
PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
Kaichun Mo, He Wang, Xinchen Yan, Leonidas Guibas
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add structure-aware tree discriminator D^struct | B-Part · PartNet Chair (test) | FPD: 11.10 -> 10.69 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Table (test) | FPD: 16.92 -> 15.33 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Cabinet (test) | FPD: 24.29 -> 17.73 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Lamp (test) | FPD: 94.66 -> 80.55 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Chair (test) | HierInsSeg score: 0.58 -> 0.48 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Cabinet (test) | HierInsSeg score: 0.81 -> 0.57 | Improved |
| add structure-aware tree discriminator D^struct | B-Part · PartNet Chair (test) | part coverage: 0.41 -> 0.07 | Improved |
| use part-based tree generator instead of whole-shape MLP generator | B-Whole · PartNet Chair (test) | FPD: 10.88 -> 11.10 | No clear effect |
| use part-based tree generator instead of whole-shape MLP generator | B-Whole · PartNet Lamp (test) | FPD: 86.96 -> 94.66 | Hurt |
| add holistic discriminator D^whole (ablation) | Ours without D^whole · PartNet Chair (test) | FPD: 13.52 -> 10.69 | Improved |
| add holistic discriminator D^whole (ablation) | Ours without D^whole · PartNet Chair (test) | shape diversity: 0.21 -> 0.18 | Hurt |
| add holistic discriminator D^whole (ablation) | Ours without D^whole · PartNet Chair (test) | HierInsSeg score: 0.49 -> 0.48 | Improved |
Closest papers by meaning
- Discrete Point Flow Networks for Efficient Point Cloud Generation (ECCV 2020 · similarity 0.90)
- EditVAE: Unsupervised Parts-Aware Controllable 3D Point Cloud Shape Generation (AAAI 2022 · similarity 0.90)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 2025 · similarity 0.89)
- Learning Gradient Fields for Shape Generation (ECCV 2020 · similarity 0.89)
- Learning Representations and Generative Models for 3D Point Clouds (ICML 2018 · similarity 0.89)
- GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation (ICLR 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.
