AI Paper Atlas

Research map / 3D vision / Face and shape

N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations

Qingyang Tan, Zherong Pan, Breannan Smith, Takaaki Shiratori, Dinesh Manocha

ICML 2022 · 3D vision › Face and shape · approach: Textured mesh generation · 0 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
Use active, risk-seeking data aggregation instead of random supervised samplingNeural collision detector · SCAPE, Swing, Jump, Skirt, and Handaccuracy: 0.9282 -> 0.9383; 0.9609 -> 0.9638; 0.9500 -> 0.9552; 0.9795 -> 0.9817; 0.9650 -> 0.9692Improved
Use active, risk-seeking data aggregation instead of random supervised samplingNeural collision detector · SCAPE, Swing, Jump, Skirt, and Handfalse negative rate: 0.05576 -> 0.05151; 0.01766 -> 0.01485; 0.02644 -> 0.02573; 0.01956 -> 0.01808; 0.03652 -> 0.03582Improved
Use active, risk-seeking data aggregation instead of random supervised samplingCollision handler using ALM · Unseen self-penetrating meshescollision-handling success rate: 24.74% more collisions than Supv + bdImproved
Add boundary loss for samples near the collision decision boundary (ablation)Supervised collision detector · Collision handlingcollision-handling success rateImproved
Add active data aggregation that samples toward the learned decision boundaryCollision handler using ALM · Collision-handling success rate across dataset sizescollision-handling success rateImproved
Use active + bd instead of Supv + bdCollision handler on SCAPE · SCAPEmean relative PD reduction: 88.76% -> 94.81%Improved
Use active + bd instead of Supv + bdCollision handler on SCAPE · SCAPEmean embedding difference: 66.11 -> 56.17Improved

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