http://hdl.handle.net/2451/43778 2026-04-11T14:52:56Z http://hdl.handle.net/2451/61215 Title: ABC Dataset Metainformation Authors: Koch, Sebastian; Matveev, Albert; Jiang, Zhongshi; Williams, Francis; Artemov, Alexey; Burnaev, Evgeny; Alexa, Marc; Zorin, Denis; Panozzo, Daniele 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. Description: ABC Dataset Metainformation. The dataset is released under the MIT License. We are grateful to Onshape for providing the CAD models and support. The copyright of these CAD models is owned by their creators. For licensing details, see Onshape Terms of Use 1.g.ii. (https://www.onshape.com/legal/terms-of-use#your_content). 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. For more information visit the ABC dataset website https://deep-geometry.github.io/abc-dataset 2019-01-01T00:00:00Z http://hdl.handle.net/2451/59958 Title: ABC Dataset Normal Estimation Benchmark Authors: Koch, Sebastian; Matveev, Albert; Jiang, Zhongshi; Williams, Francis; Artemov, Alexey; Burnaev, Evgeny; Alexa, Marc; Zorin, Denis; Panozzo, Daniele 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. Description: ABC Dataset Normal Estimation Benchmark. The dataset is released under the MIT License. We are grateful to Onshape for providing the CAD models and support. The copyright of these CAD models is owned by their creators. For licensing details, see Onshape Terms of Use 1.g.ii. (https://www.onshape.com/legal/terms-of-use#your_content). 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. For more information visit the ABC dataset website https://deep-geometry.github.io/abc-dataset 2019-01-01T00:00:00Z http://hdl.handle.net/2451/44418 Title: ABC Dataset Chunk 0099 Authors: Koch, Sebastian; Matveev, Albert; Jiang, Zhongshi; Williams, Francis; Artemov, Alexey; Burnaev, Evgeny; Alexa, Marc; Zorin, Denis; Panozzo, Daniele 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. Description: ABC Dataset Chunk 0099 (10k objects). The dataset is released under the MIT License. We are grateful to Onshape for providing the CAD models and support. The copyright of these CAD models is owned by their creators. For licensing details, see Onshape Terms of Use 1.g.ii. (https://www.onshape.com/legal/terms-of-use#your_content). 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. For more information visit the ABC dataset website https://deep-geometry.github.io/abc-dataset 2019-01-01T00:00:00Z http://hdl.handle.net/2451/44417 Title: ABC Dataset Chunk 0089 Authors: Koch, Sebastian; Matveev, Albert; Jiang, Zhongshi; Williams, Francis; Artemov, Alexey; Burnaev, Evgeny; Alexa, Marc; Zorin, Denis; Panozzo, Daniele 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. Description: ABC Dataset Chunk 0089 (10k objects). The dataset is released under the MIT License. We are grateful to Onshape for providing the CAD models and support. The copyright of these CAD models is owned by their creators. For licensing details, see Onshape Terms of Use 1.g.ii. (https://www.onshape.com/legal/terms-of-use#your_content). 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. For more information visit the ABC dataset website https://deep-geometry.github.io/abc-dataset 2019-01-01T00:00:00Z