Presentation
Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
SessionNumerical Geometry a la Mode
DescriptionNEO is a neural framework for fast Laplace-Beltrami spectral analysis on 3D point clouds. Rather than computing eigenvectors with expensive iterative solvers, it predicts low-frequency eigenspaces directly from geometry, enabling near-linear scaling, robustness to irregular sampling, and accurate zero-shot transfer to substantially higher-resolution shapes and downstream spectral tasks.
Event Type
Technical Paper
TimeMonday, 20 July 20269:10am - 9:20am PDT
LocationRoom 408 B
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 20269:00am - 10:05am PDTRoom 408 B
Artificial Intelligence/Machine Learning
Geometry
Modeling
Full Conference Supporter
Full Conference
