{"url":"/dataset/p2s","name":"P2S","full_name":"Points2Surf","description_markdown":"We introduced this dataset in Points2Surf, a method that turns point clouds into meshes.\r\n\r\nIt consists of objects from the [_ABC Dataset_](https://paperswithcode.com/dataset/abc-dataset-1), a collection of _Famous_ meshes and objects from [_Thingi10k_](https://paperswithcode.com/dataset/thingi10k).\r\nThese are mostly single objects per file, sometimes a couple of disconnected objects. Objects from the _ABC Dataset_ are CAD-models, the others are mostly statues with organic structures.\r\n\r\nWe created realistic point clouds using a simulated time-of-flight sensor from [_BlenSor_](https://www.blensor.org/). The point clouds have typical artifacts like noise and scan shadows.\r\n\r\nFinally, we created training data consisting of randomly sampled query points with their ground-truth signed distance. The query points are 50% uniformly distributed in the unit cube and 50% near the surface with some random offset.\r\n\r\nThe training set consists of 4950 _ABC_ objects with varying number of scans and noise strength. \r\nThe validation sets are the same as the test set. \r\nThe _ABC_ test sets contain 100 objects, _Famous_ 22 and _Thingi10k_ 100. The test set variants are as follows:\r\n(1) _ABC_ var (like training set), no noise, strong noise; \r\n(2) _Famous_ no noise, medium noise, strong noise, sparse, dense scans;\r\n(3) _Thingi10k_ no noise, medium noise, strong noise, sparse, dense scans","description_withheld":null,"homepage":"https://www.cg.tuwien.ac.at/research/publications/2020/erler-2020-p2s/","introduced_date":"2020-07-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/points2surf-learning-implicit-surfaces-from","title":"Points2Surf: Learning Implicit Surfaces from Point Cloud Patches","first_author":"Philipp Erler","url":null},"license":null,"modalities":[{"name":"Point cloud","url":"/datasets/modality/point-cloud"},{"name":"3d meshes","url":"/datasets/modality/3d-meshes"}],"tasks":[{"name":"Surface Reconstruction","url":"/task/surface-reconstruction","datasets_with_task":"/datasets/task/surface-reconstruction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["P2S"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}