Haotian Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haotian Yin has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Przemyslaw Musialski
New Jersey Institute of Technology (NJIT), Newark, USA
3 shared publications - Aleksander Plocharski
Warsaw University of Technology, Warsaw, Poland and IDEAS NCBR, Warsaw, Poland
2 shared publications - Michal Jan Wlodarczyk
Warsaw University of Technology, Warsaw, Masovian, Poland
2 shared publications - Heather Yu
Futurewei Technologies Inc, Santa Clara, USA
1 shared publication - Jiali Cui
Futurewei Technologies, Inc., Basking Ridge, USA
1 shared publication - Jiaxing Zhang
New Jersey Institute of Technology, USA
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Where to Learn Matters: Feature-Aware Sampling for Neural SDF Reconstruction
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessWhere to Learn Matters: Feature-Aware Sampling for Neural SDF Reconstruction
- Open Access
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
A Finite Difference Approximation of Second Order Regularization of Neural-SDFs
- 15 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessA Finite Difference Approximation of Second Order Regularization of Neural-SDFs
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models
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 finite‐difference 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/.
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models
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 finite‐difference 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/.