Research map / Point clouds / Shape and surface completion
Hypernetwork approach to generating point clouds
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 HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Airplane | JSD: 4.92 -> 4.84 | No clear effect |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Airplane | MMD-CD: 0.217 -> 0.266 | Hurt |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Airplane | MMD-EMD: 3.24 -> 3.28 | No clear effect |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Chair | MMD-EMD: 7.87 -> 7.84 | No clear effect |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Car | JSD: 0.87 -> 3.09 | Hurt |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Car | MMD-CD: 0.91 -> 1.07 | Hurt |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Car | MMD-EMD: 5.22 -> 5.38 | Hurt |
| Use HyperCloud instead of PointFlow | 3D point-cloud generation · ShapeNet Chair | MMD-EMD: 7.87 -> 7.84 | Helped |
| Use HyperCloud with a uniform unit-ball prior rather than PointFlow with Gaussian prior | mesh-surface sampling · ShapeNet Airplane | JSD: 22.26 -> 9.51 | Helped |
| Use HyperCloud with a uniform unit-ball prior rather than PointFlow with Gaussian prior | mesh-surface sampling · ShapeNet Chair | COV-CD: 36.85 -> 40.33 | Helped |
| Use HyperCloud with a uniform unit-ball prior rather than PointFlow with Gaussian prior | mesh-surface sampling · ShapeNet Car | JSD: 16.59 -> 5.20 | Helped |
Closest papers by meaning
- A Point Set Generation Network for 3D Object Reconstruction From a Single Image (CVPR 2017 · similarity 0.89)
- Hyper-PCN: Hypergraph-Based Point Cloud Completion via High-Order Correlation Modeling (CVPR 2026 · similarity 0.89)
- TopNet: Structural Point Cloud Decoder (CVPR 2019 · similarity 0.89)
- Learning Progressive Point Embeddings for 3D Point Cloud Generation (CVPR 2021 · similarity 0.88)
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction (AAAI 2018 · similarity 0.88)
- 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.