TY - GEN
T1 - ABC
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
AU - Koch, Sebastian
AU - Matveev, Albert
AU - Jiang, Zhongshi
AU - Williams, Francis
AU - Artemov, Alexey
AU - Burnaev, Evgeny
AU - Alexa, Marc
AU - Zorin, Denis
AU - Panozzo, Daniele
N1 - Funding Information:
We are grateful to Onshape for providing the CAD models and support. This work was supported in part through the NYU IT High Performance Computing resources, services, and staff expertise. Funding provided by NSF award MRI-1229185. We thank the Skoltech CDISE HPC Zhores cluster staff for computing cluster provision. This work was supported in part by NSF CAREER award 1652515, the NSF grants IIS-1320635, DMS-1436591, and 1835712, the Russian Science Foundation under Grant 19-41-04109, and gifts from Adobe Research, nTopology Inc, and NVIDIA.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - 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.
AB - 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.
KW - Big Data
KW - Categorization
KW - Datasets and Evaluation
KW - Deep Learning
KW - Large Scale Methods
KW - Recognition: Detection
KW - Retrieval
KW - S
UR - http://www.scopus.com/inward/record.url?scp=85077504496&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077504496&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00983
DO - 10.1109/CVPR.2019.00983
M3 - Conference contribution
AN - SCOPUS:85077504496
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 9593
EP - 9603
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
Y2 - 16 June 2019 through 20 June 2019
ER -