{"url":"/dataset/transcg","name":"TransCG","full_name":"TransCG","description_markdown":"TransCG is the first large-scale real-world dataset for transparent object depth completion and grasping, which contains 57,715 RGB-D images of 51 transparent objects and many opaque objects captured from different perspectives (~240 viewpoints) of 130 scenes under real-world settings. The samples are captured by two different types of cameras (Realsense D435 & L515).\r\n\r\nThe following data is provided:\r\n\r\n- The 3D model of the transparent object;\r\n- The 6dpose of the transparent object in each viewpoint of each scene;\r\n- The raw RGB-D image, and the ground-truth refined depth image;\r\n- The mask of the transparent objects;\r\n- The ground-truth surface normals of every sample.","description_withheld":null,"homepage":"https://graspnet.net/transcg","introduced_date":"2022-02-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/transcg-a-large-scale-real-world-dataset-for","title":"TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline","first_author":"Hongjie Fang","url":null},"license":{"name":"CC-BY-NC-SA","url":"https://en.wikipedia.org/wiki/Creative_Commons_NonCommercial_license"},"modalities":[{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Depth Completion","url":"/task/depth-completion","datasets_with_task":"/datasets/task/depth-completion"},{"name":"Transparent Object Depth Estimation","url":"/task/transparent-object-depth-estimation","datasets_with_task":"/datasets/task/transparent-object-depth-estimation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TransCG"],"data_loaders":[{"repo":"https://github.com/galaxies99/transcg","url":"https://graspnet.net/transcg","frameworks":["pytorch"]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/transparent-object-depth-estimation-on","task":"Transparent Object Depth Estimation","dataset_variant":"TransCG","rows":1,"metrics":["Delta < 1.25","MAE","REL","RMSE","delta < 1.05","delta < 1.10"],"first_row_in_archive_order":{"model":"DFNet","paper":"/paper/transcg-a-large-scale-real-world-dataset-for","metrics":{"Delta < 1.25":"99.71","MAE":"0.012","REL":"0.027","RMSE":"0.018","delta < 1.05":"83.76","delta < 1.10":"95.67"},"code_links":[{"title":"galaxies99/transcg","url":"https://github.com/galaxies99/transcg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/transcg-a-large-scale-real-world-dataset-for","title":"TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline","date":"2022-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}