FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models
| dc.contributor.author | Yin, Haotian | en_US |
| dc.contributor.author | Plocharski, Aleksander | en_US |
| dc.contributor.author | Wlodarczyk, Michal Jan | en_US |
| dc.contributor.author | Kida, Mikolaj | en_US |
| dc.contributor.author | Musialski, Przemyslaw | en_US |
| dc.contributor.editor | Christie, Marc | en_US |
| dc.contributor.editor | Pietroni, Nico | en_US |
| dc.contributor.editor | Wang, Yu-Shuen | en_US |
| dc.date.accessioned | 2025-10-07T05:02:24Z | |
| dc.date.available | 2025-10-07T05:02:24Z | |
| dc.date.issued | 2025 | |
| dc.description.abstract | Neural 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.number | 7 | |
| dc.description.sectionheaders | Lines, Surfaces & Fields | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 44 | |
| dc.identifier.doi | 10.1111/cgf.70249 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 12 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.70249 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.1111/cgf70249 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | CCS Concepts: Computing methodologies → Shape modeling; Regularization; Machine learning algorithms | |
| dc.subject | Computing methodologies → Shape modeling | |
| dc.subject | Regularization | |
| dc.subject | Machine learning algorithms | |
| dc.title | FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models | en_US |