AI Paper Atlas

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

NeurIPS 2022 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
train 1000 epochs instead of 100 (ablation)CurveNet · intrinsic dim 2MSE x10^3: 14.071 -> 2.115Improved
train 1000 epochs instead of 100 (ablation)CurveNet · intrinsic dim 5MSE x10^3: 4.865 -> 0.964Improved
train 1000 epochs instead of 100 (ablation)CurveNet · intrinsic dim 10MSE x10^3: 0.798 -> 0.752No clear effect
train 1000 epochs instead of 100 (ablation)CurveNet · intrinsic dim 15MSE x10^3: 0.085 -> 0.766Hurt
train 1000 epochs instead of 100 (ablation)CurveNet · intrinsic dim 20MSE x10^3: 0.082 -> 0.712Hurt
CurveNet vs random baselineCurveNet · intrinsic dim 2MSE x10^3: 612.145 -> 2.115Improved
CurveNet vs random baselineCurveNet · intrinsic dim 20MSE x10^3: 515.739 -> 0.712Improved
diffusion curvature vs Gaussian curvature on toy surfacesDiffusion Curvature · synthetic surfacescorrelationImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy