Presentation

· Contributors · Organizations · Search Program · My Schedule · Happening Now · Maps

NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvature

DescriptionIn this paper, we present a self-supervised neural representation aimed at reconstructing CAD models from low-quality, unoriented point clouds. Our approach stands out from traditional reconstruction methods by applying a zero Gaussian curvature constraint, which emphasizes the characteristic of being almost developable and enhances the preservation of feature points/lines.

Authors

Qiujie Dong

Shandong University