{"url":"/dataset/modelnet40-c","name":"ModelNet40-C","full_name":"ModelNet-C","description_markdown":"ModelNet40-C is a comprehensive dataset to benchmark the corruption robustness of 3D point cloud recognition.\r\n\r\nWe create ModelNet40-C based on the ModelNet40 validation set with 15 corruption types and 5 severity levels for each corruption type including density, noise, and transformation corruption patterns. Our dataset contains 185,000 distinct point clouds that help provide a comprehensive picture of model robustness.","description_withheld":null,"homepage":"https://sites.google.com/umich.edu/modelnet40c","introduced_date":"2022-01-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/benchmarking-robustness-of-3d-point-cloud","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","first_author":"Jiachen Sun","url":null},"license":{"name":"BSD 3-Clause","url":"https://github.com/jiachens/ModelNet40-C/blob/master/LICENSE"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"}],"tasks":[{"name":"3D Point Cloud Classification","url":"/task/3d-point-cloud-classification","datasets_with_task":"/datasets/task/3d-point-cloud-classification"},{"name":"3D Classification","url":"/task/3d-classification","datasets_with_task":"/datasets/task/3d-classification"},{"name":"3D Point Cloud Data Augmentation","url":"/task/3d-point-cloud-data-augmentation","datasets_with_task":"/datasets/task/3d-point-cloud-data-augmentation"},{"name":"Few-Shot Point Cloud Classification","url":"/task/few-shot-point-cloud-classification","datasets_with_task":"/datasets/task/few-shot-point-cloud-classification"},{"name":"Robust classification","url":"/task/robust-classification","datasets_with_task":"/datasets/task/robust-classification"},{"name":"Classify 3D Point Clouds","url":"/task/classify-3d-point-clouds","datasets_with_task":"/datasets/task/classify-3d-point-clouds"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ModelNet40-C"],"data_loaders":[{"repo":"https://github.com/jiachens/ModelNet40-C","url":"https://github.com/jiachens/ModelNet40-C","frameworks":["pytorch"]}],"num_papers_in_archive":32,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40-c","task":"3D Point Cloud Classification","dataset_variant":"ModelNet40-C","rows":13,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"Error Rate":"0.142"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-point-cloud-classification-on-1","task":"Few-Shot Point Cloud Classification","dataset_variant":"ModelNet40-C","rows":1,"metrics":["Top-1 Accuracy(5-Way-1-Shot)"],"first_row_in_archive_order":{"model":"ViewNet","paper":"/paper/viewnet-a-novel-projection-based-backbone","metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"79.09"},"code_links":[{"title":"jiajingchen113322/ViewNet","url":"https://github.com/jiajingchen113322/ViewNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/viewnet-a-novel-projection-based-backbone","title":"ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/benchmarking-robustness-of-3d-point-cloud","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","date":"2022-01-28","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":29,"samples_ran":14,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/regularization-strategy-for-point-cloud-via","title":"Regularization Strategy for Point Cloud via Rigidly Mixed Sample","date":"2021-02-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointcutmix-regularization-strategy-for-point","title":"PointCutMix: Regularization Strategy for Point Cloud Classification","date":"2021-01-05","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-point-cloud-classification-with-a","title":"Revisiting Point Cloud Classification with a Simple and Effective Baseline","date":"2021-01-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pct-point-cloud-transformer","title":"PCT: Point cloud transformer","date":"2020-12-17","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointmixup-augmentation-for-point-clouds","title":"PointMixup: Augmentation for Point Clouds","date":"2020-08-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/relation-shape-convolutional-neural-network","title":"Relation-Shape Convolutional Neural Network for Point Cloud Analysis","date":"2019-04-16","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-graph-cnn-for-learning-on-point","title":"Dynamic Graph CNN for Learning on Point Clouds","date":"2018-01-24","rows_on_this_dataset":1,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":44,"samples_ran":16,"samples_unverified":28,"pointer_only_for_licence":31,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointnet-deep-hierarchical-feature-learning","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","date":"2017-06-07","rows_on_this_dataset":1,"code_links":68,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":67,"samples_ran":36,"samples_unverified":31,"pointer_only_for_licence":26,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointnet-deep-learning-on-point-sets-for-3d","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","date":"2016-12-02","rows_on_this_dataset":1,"code_links":110,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":164,"samples_ran":89,"samples_unverified":75,"pointer_only_for_licence":90,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":315,"samples_ran":163,"samples_unverified":152,"pointer_only_for_licence":147,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}