ABC: A Big CAD Model Dataset For Geometric Deep Learning
This provides a foundational resource for researchers in geometric deep learning, facilitating fair comparisons and advancing applications in CAD and 3D modeling.
The authors introduced ABC-Dataset, a collection of one million CAD models to address the lack of large-scale datasets for geometric deep learning, enabling benchmarks like surface normal estimation where data-driven methods showed performance gains over traditional approaches.
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.