REVIEW 4 cited by
Geometry-Informed Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Geometry-Informed Neural Networks
read the original abstract
Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative learning strategies. To this end, we introduce geometry-informed neural networks (GINNs) -- a framework for training shape-generative neural fields without data by leveraging user-specified design requirements in the form of objectives and constraints. By adding diversity as an explicit constraint, GINNs avoid mode-collapse and can generate multiple diverse solutions, often required in geometry tasks. Experimentally, we apply GINNs to several problems spanning physics, geometry, and engineering design, showing control over geometrical and topological properties, such as surface smoothness or the number of holes. These results demonstrate the potential of training shape-generative models without data, paving the way for new generative design approaches without large datasets.
Forward citations
Cited by 4 Pith papers
-
GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
-
Neural Representation of Minimal Surfaces
Complex-valued neural nets for two holomorphic spinor functions yield minimal surfaces by construction and can be trained to match prescribed Plateau boundaries.
-
GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer
GIBLy is an architecture-agnostic lightweight layer that adds learnable geometric priors aligned with simple shapes to 3D semantic segmentation pipelines, delivering consistent mIoU gains (up to +11.5% on TS40K) with ...
-
Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization
NOTES couples a DeepONet topology decoder with CMA-ES in a PCA-derived latent space, achieving >95% deflection efficiency on nanophotonic metagratings and compliance of 246 on MBB beams, outperforming direct CMA-ES an...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.