Research map / Point clouds / Shape and surface completion
General Hypernetwork Framework for Creating 3D Point Clouds
Przemyslaw Spurek, Maciej Zięba, Jacek Tabor, T. P. Trzcinski
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 |
|---|---|---|---|
| use HyperCloud instead of PointFlow when sampling points from a sphere surface | HyperCloud · ShapeNet airplane, sphere sampling | JSD: 22.26 -> 9.51 | Improved |
| use HyperCloud instead of PointFlow on sphere sampling | HyperCloud · ShapeNet chair, sphere sampling | JSD: 19.28 -> 4.32 | Improved |
| use HyperCloud instead of PointFlow on sphere sampling | HyperCloud · ShapeNet car, sphere sampling | MMD-CD: 1.6 -> 1.11 | Improved |
| increase PointFlow sphere radius from 2.795 to 3.368 | PointFlow · ShapeNet airplane, sphere sampling | JSD: 22.26 -> 29.65 | Hurt |
| increase PointFlow sphere radius from 2.795 to 3.368 | PointFlow · ShapeNet chair, sphere sampling | MMD-CD: 4.28 -> 5.36 | Hurt |
| use PointFlow instead of HyperCloud for generation | HyperCloud · ShapeNet chair generation | 1-NNA-CD: 68.20 -> 60.88 | Hurt |
| use PointFlow instead of HyperCloud for generation | HyperCloud · ShapeNet car generation | 1-NNA-CD: 84.65 -> 60.65 | Hurt |
| compare HyperCloud with EMD-loss GAN l-GAN (EMD) | HyperCloud · ShapeNet airplane generation | 1-NNA-EMD: 88.95 vs 85.68 | No clear effect |
Closest papers by meaning
- Hypernetwork approach to generating point clouds (ICML 2020 · similarity 0.99)
- Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling (CVPR 2026 · similarity 0.90)
- A Point Set Generation Network for 3D Object Reconstruction From a Single Image (CVPR 2017 · similarity 0.89)
- Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance (ECCV 2020 · similarity 0.89)
- TopNet: Structural Point Cloud Decoder (CVPR 2019 · similarity 0.89)
- HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories (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.
