Presentation

· Contributors · Organizations · Search Program

Split-and-Fit: Learning B-Reps via Structure-aware Voronoi Partitioning

DescriptionThe "Split-and-Fit" method introduces a top-down, structure-aware strategy for reconstructing B-Rep models, using Voronoi diagrams to partition the space and followed by primitive fitting. We design NVD-Net to accurately predict these partitions from point clouds or distance fields, resulting in significantly improved reconstruction quality and generalizability compared to previous methods.

Authors

Yilin Liu

Shenzhen University

Simon Fraser University