Neural Stochastic Poisson Surface Reconstruction
DescriptionReconstructing a surface from a point cloud is an underdetermined problem. We propose using a neural network to study and quantify this reconstruction uncertainty under a Poisson smoothness prior. Our algorithm addresses the main limitations of existing work and can be fully integrated into the 3D scanning pipeline, from deciding on the next best sensor position to iteratively updating the reconstruction upon capturing more data.
Event Type
Technical Papers
TimeTuesday, 12 December 20239:30am - 12:45pm
LocationDarling Harbour Theatre, Level 2 (Convention Centre)
