DualBrep encodes B-rep models as dual scalar fields (SDF geometry + UDF topology) compressed into a shared latent space for flow-matching generation and neural B-rep extraction.
Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DualBrep: A Dual-Field Continuous Representation for B-rep Modelling
DualBrep encodes B-rep models as dual scalar fields (SDF geometry + UDF topology) compressed into a shared latent space for flow-matching generation and neural B-rep extraction.