Research map / Point clouds / Shape and surface completion
Diffusion Curvature for Estimating Local Curvature in High Dimensional Data
Dhananjay Bhaskar, Kincaid MacDonald, Oluwadamilola Fasina, Dawson S Thomas, Bastian Rieck, Ian Adelstein, Smita Krishnaswamy
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 |
|---|---|---|---|
| train 1000 epochs instead of 100 (ablation) | CurveNet · intrinsic dim 2 | MSE x10^3: 14.071 -> 2.115 | Improved |
| train 1000 epochs instead of 100 (ablation) | CurveNet · intrinsic dim 5 | MSE x10^3: 4.865 -> 0.964 | Improved |
| train 1000 epochs instead of 100 (ablation) | CurveNet · intrinsic dim 10 | MSE x10^3: 0.798 -> 0.752 | No clear effect |
| train 1000 epochs instead of 100 (ablation) | CurveNet · intrinsic dim 15 | MSE x10^3: 0.085 -> 0.766 | Hurt |
| train 1000 epochs instead of 100 (ablation) | CurveNet · intrinsic dim 20 | MSE x10^3: 0.082 -> 0.712 | Hurt |
| CurveNet vs random baseline | CurveNet · intrinsic dim 2 | MSE x10^3: 612.145 -> 2.115 | Improved |
| CurveNet vs random baseline | CurveNet · intrinsic dim 20 | MSE x10^3: 515.739 -> 0.712 | Improved |
| diffusion curvature vs Gaussian curvature on toy surfaces | Diffusion Curvature · synthetic surfaces | correlation | Improved |
Closest papers by meaning
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.88)
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.87)
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (ICML 2024 · similarity 0.86)
- Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates (NeurIPS 2025 · similarity 0.86)
- Manifold Diffusion Fields (ICLR 2024 · similarity 0.86)
- Diffusion Models Encode the Intrinsic Dimension of Data Manifolds (ICML 2024 · 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.
