ModelNet10, ModelNet40, and ScanObjectNN

doi:doi:10.57702/jvwgg65m

ModelNet10, ModelNet40, and ScanObjectNN

The dataset used in the PointCLIP paper is ModelNet10, ModelNet40, and ScanObjectNN. ModelNet10 consists of 4,899 synthetic meshed CAD models with 10 indoor categories, 3,991 for training and 908 for testing. ModelNet40 is larger and contains 12,311 samples of 40 common categories, 9,843 for training and 2,468 for testing. ScanObjectNN contains 2,321 training and 581 testing point clouds of 15 categories collected directly from real-world scans.

BibTex:

@dataset{Renrui_Zhang_and_Ziyu_Guo_and_Wei_Zhang_and_Kunchang_Li_and_Xupeng_Miao_and_Bin_Cui_and_Yu_Qiao_and_Peng_Gao_and_Hongsheng_Li_2024,
    abstract = {The dataset used in the PointCLIP paper is ModelNet10, ModelNet40, and ScanObjectNN. ModelNet10 consists of 4,899 synthetic meshed CAD models with 10 indoor categories, 3,991 for training and 908 for testing. ModelNet40 is larger and contains 12,311 samples of 40 common categories, 9,843 for training and 2,468 for testing. ScanObjectNN contains 2,321 training and 581 testing point clouds of 15 categories collected directly from real-world scans.},
    author = {Renrui Zhang and Ziyu Guo and Wei Zhang and Kunchang Li and Xupeng Miao and Bin Cui and Yu Qiao and Peng Gao and Hongsheng Li},
    doi = {10.57702/jvwgg65m},
    institution = {No Organization},
    keyword = {'3D Object Recognition', 'CAD Models', 'Point Clouds'},
    month = {dec},
    publisher = {TIB},
    title = {ModelNet10, ModelNet40, and ScanObjectNN},
    url = {https://service.tib.eu/ldmservice/dataset/modelnet10--modelnet40--and-scanobjectnn},
    year = {2024}
}