Research map / Point clouds / Shape and surface completion
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
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 |
|---|---|---|---|
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet airplane | 1-NNA CD (%): 75.68 -> 70.92 | Helped |
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet airplane | 1-NNA EMD (%): 75.06 -> 69.44 | Helped |
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet chair | 1-NNA CD (%): 60.88 -> 59.95 | Helped |
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet chair | 1-NNA EMD (%): 59.89 -> 63.51 | Hurt |
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet car | 1-NNA CD (%): 60.65 -> 62.63 | Hurt |
| Apply SoftFlow perturbation conditioning to PointFlow | PointFlow · ShapeNet car | 1-NNA EMD (%): 62.36 -> 64.71 | Hurt |
| Train flows on randomly perturbed data conditioned on the noise scale | FFJORD · Artificial 1D-manifold distributions | sample fit to data distribution | Helped |
Closest papers by meaning
- C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds (CVPR 2020 · similarity 0.88)
- Flows for simultaneous manifold learning and density estimation (NeurIPS 2020 · similarity 0.87)
- Not-So-Optimal Transport Flows for 3D Point Cloud Generation (ICLR 2025 · similarity 0.86)
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (NeurIPS 2026 · similarity 0.86)
- Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models (NeurIPS 2026 · similarity 0.86)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.85)
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.