DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
Registration Categories
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
DescriptionDeep Estimators of Features (DEFs) is a learning-based framework for predicting sharp geometric features in sampled 3D shapes. DEF regresses a scalar distance-to-feature field on local point patches and integrates field estimates into a complete parametric reconstruction. Our framework achieves state-of-the-art performance and scalability and generalizes to real-world scans.