Year: 2019
Type: conference-paper
Abstract: We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows generating data in different formats and resolutions, enabling fair comparisons for a wide range of geometric learning algorithms. As a use case for our dataset, we perform a large-scale benchmark for estimation of surface normals, comparing existing data driven methods and evaluating their performance against both the ground truth and traditional normal estimation methods.
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Awards: CGV: Small: Scalable high-quality surface parameterization and resampling, CAREER: Coupling Geometry Acquisition and Digital Fabrication, MRI: Acquisition of an Infrastructure for Prototyping Next-Generation Algorithms for Large-Scale Visualization, Data Processing and Analysis, G6671297155, Elements:Software:Open-Source Robust Geometry Toolkit for Black-Box Finite Element Analysis, DMREF: Adaptive Fine-Scale Structure Design: From Theory to Fabrication
OpenAlex ID: W2904866874