FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models

dc.contributor.authorYin, Haotianen_US
dc.contributor.authorPlocharski, Aleksanderen_US
dc.contributor.authorWlodarczyk, Michal Janen_US
dc.contributor.authorKida, Mikolajen_US
dc.contributor.authorMusialski, Przemyslawen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:02:24Z
dc.date.available2025-10-07T05:02:24Z
dc.date.issued2025
dc.description.abstractNeural signed-distance fields (SDFs) are a versatile backbone for neural geometry representation, but enforcing CAD-style developability usually requires Gaussian-curvature penalties with full Hessian evaluation and second-order differentiation, which are costly in memory and time. We introduce an off-diagonal Weingarten loss that regularizes only the mixed shape operator term that represents the gap between principal curvatures and flattens the surface. We present two variants: a finitedifference version using six SDF evaluations plus one gradient, and an auto-diff version using a single Hessian-vector product. Both converge to the exact mixed term and preserve the intended geometric properties without assembling the full Hessian. On the ABC benchmarks the losses match or exceed Hessian-based baselines while cutting GPU memory and training time by roughly a factor of two. The method is drop-in and framework-agnostic, enabling scalable curvature-aware SDF learning for engineering-grade shape reconstruction. Our code is available at https://flatcad.github.io/.en_US
dc.description.number7
dc.description.sectionheadersLines, Surfaces & Fields
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70249
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70249
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70249
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Shape modeling; Regularization; Machine learning algorithms
dc.subjectComputing methodologies → Shape modeling
dc.subjectRegularization
dc.subjectMachine learning algorithms
dc.titleFlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Modelsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
cgf70249.pdf
Size:
45.28 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
paper1203_mm1.mp4
Size:
40.79 MB
Format:
Video MP4
Collections