{"url":"/dataset/virdo-dataset","name":"VIRDO Dataset","full_name":"VIRDO Simulated Kitchen Utensil Deformation Dataset","description_markdown":"From https://github.com/MMintLab/VIRDO/blob/master/data/dataset_readme.txt,\r\n\r\n1. DESCRIPTION: This dataset is written in 'dtype=torch.float64'. This dataset consists of total 144 deformation scenes from 6 different objects generated through MATLAB. It is divided into 'train' and 'test' dataset, where data['train'][OBJECT IDX = i][DEFORM IDX = j ] and data['test'][OBJECT IDX = i][DEFORM IDX = j ] indicates the same scene, but they are two different subsets of query points.\r\n\r\n\r\n2. STRUCTURE: The dataset structure is as follows:\r\nVIRDO_simul_dataset = {\r\n'train':{\r\n\t<OBJECT IDX>: {\r\n\t\t'nominal': {\r\n\t\t\t'coords': tensor([1, M, 3]),\r\n\t\t\t'normals': tensor([1, M, 3]),\r\n\t\t\t'gt': tensor([1, M, 3]),\r\n\t\t\t'scale': float\r\n\t\t\t},\r\n\t\t<DEFORM IDX>: {\r\n\t\t\t'coords': tensor([1, M, 3]),\r\n\t\t\t'contact': tensor([1, M_c, 3]),\r\n\t\t\t'normals': tensor([1, M, 3]),\r\n\t\t\t'gt': tensor([1, M, 3]),\r\n\t\t\t'scale': float,\r\n\t\t\t'reaction': tensor([1,3]\r\n\t\t\t},\r\n\t\t},\r\n\t\t\r\n\t},\r\n'test':{\r\n\t<OBJECT IDX>: {\r\n\t\t'nominal': {\r\n\t\t\t'coords': tensor([1, M, 3]),\r\n\t\t\t'normals': tensor([1, M, 3]),\r\n\t\t\t'gt': tensor([1, M, 3]),\r\n\t\t\t'scale': float\r\n\t\t\t},\r\n\t\t<DEFORM IDX>: {\r\n\t\t\t'coords': tensor([1, M, 3]),\r\n\t\t\t'contact': tensor([1, M_c, 3]),\r\n\t\t\t'normals': tensor([1, M, 3]),\r\n\t\t\t'gt': tensor([1, M, 3]),\r\n\t\t\t'scale': float,\r\n\t\t\t'reaction': tensor([1,3]\r\n\t\t\t},\r\n\t\t},\r\n\t\t\r\n\t},\r\n}\r\n\r\n\t* <OBJECT IDX> = Interger from 0 ~ 5. Each number indicates different object.\r\n\t* <DEFORM IDX> = Unique integer for each deformation.\r\n\t* M = total points (on-surface + off-surface)\r\n\t* M_c = a subset of on-surface points that are in contact\r\n\t* [:,i,:] elements of 'coords', 'normals', and 'gt' refers ith query point of a scene. To get on-surface points of data_def = data['train'][<OBJECT IDX>][<DEFORM IDX>], you should do data_def['coords'][:,torch.where(data_def['gt'] == 0)[1],:].","description_withheld":null,"homepage":"https://github.com/MMintLab/VIRDO/","introduced_date":"2022-02-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/virdo-visio-tactile-implicit-representations","title":"VIRDO: Visio-tactile Implicit Representations of Deformable Objects","first_author":null,"url":null},"license":null,"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"Point cloud","url":"/datasets/modality/point-cloud"}],"tasks":[{"name":"Surface Reconstruction","url":"/task/surface-reconstruction","datasets_with_task":"/datasets/task/surface-reconstruction"},{"name":"Deformable Object Manipulation","url":"/task/deformable-object-manipulation","datasets_with_task":"/datasets/task/deformable-object-manipulation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VIRDO Dataset"],"data_loaders":[],"num_papers_in_archive":1,"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":"2026-09-24T18:15:14+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."}