{"url":"/dataset/vicos-towel-dataset","name":"ViCoS Towel Dataset","full_name":null,"description_markdown":"The ViCoS Towel Dataset is a state-of-the-art benchmark for grasp point localization on cloth objects, specifically towels. Designed to advance research in robotic grasping and perception for textile objects, this dataset includes a collection of 8,000 high-resolution RGB-D images (1920×1080) captured with a Kinect V2 under a variety of conditions. Each image provides detailed depth information, making it ideal for training deep learning models and conducting thorough benchmarking.\r\n\r\n**Object Diversity**  \r\nThe dataset features 10 types of towels from the [Household Cloth Objects](https://www.iri.upc.edu/groups/perception/ClothObjectSet/). including various sizes and patterns such as big towels, checkered rags, and waffle rags. Each towel's corners are treated as potential grasp points for detection and localization.\r\n\r\n**Object Positions**  \r\nTowels were positioned in 10 different configurations on a tabletop to simulate a range of visibility scenarios, from fully spread-out to crumpled and folded, providing diverse grasping conditions.\r\n\r\n**Background Variability**  \r\nTo enhance background variability, we used five different tabletop cloths or objects, including festive tablecloths and patterned tablecloths. This variation helps test algorithms under different background conditions.\r\n\r\n**Lighting Conditions**  \r\nImages were captured under eight distinct lighting setups, ranging from no light to fully illuminated scenes with various shadow intensities. This variety helps in evaluating the robustness of grasping models under different lighting scenarios.\r\n\r\n**Clutter**  \r\nBoth cluttered and uncluttered scenes were included to create challenging conditions with occlusions. Various clutter items were added on the desk or directly on the towels to simulate realistic scenarios.\r\n\r\n### Annotations\r\n\r\nEach visible corner of the towels in the images has been manually annotated as a potential grasping point. Annotations include a point label and the angle-of-approach, providing a total of 20,784 annotated points with corresponding angles.\r\n\r\n### Training and Testing Splits\r\n\r\nThe dataset is divided into training and testing subsets. Two towels (checkered rag small and cotton napkin) and one background (festive tablecloth) were reserved for testing, ensuring that these elements are not present in the training set. The dataset includes 5,120 training images and 2,880 testing images, covering all object configurations, lighting conditions, and clutter scenarios.\r\n\r\n### Synthetic Training Data\r\n\r\nIn addition to the real images, the dataset includes 12,000 synthetic images generated using the MuJoCo simulation environment. These synthetic images depict towels in varied positions and conditions, with different textures and lighting settings, providing further diversity for training purposes.\r\n\r\nFor more details and access to the dataset, visit [GitHub repository](https://github.com/vicoslab/CeDiRNet-3DoF?tab=readme-ov-file#vicos-towel-dataset).\r\n\r\n\r\n![CeDiRNet-3DoF: Center Direction Network for Grasping Point Localization on Cloths!](https://github.com/vicoslab/CeDiRNet-3DoF/blob/master/dataset.png?raw=true \"CeDiRNet-3DoF\")","description_withheld":null,"homepage":"https://github.com/vicoslab/CeDiRNet-3DoF#vicos-towel-dataset","introduced_date":"2024-08-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/center-direction-network-for-grasping-point","title":"Center Direction Network for Grasping Point Localization on Cloths","first_author":"Domen Tabernik","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License","url":"http://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"}],"tasks":[{"name":"Keypoint Detection","url":"/task/keypoint-detection","datasets_with_task":"/datasets/task/keypoint-detection"},{"name":"Robotic Grasping","url":"/task/robotic-grasping","datasets_with_task":"/datasets/task/robotic-grasping"}],"languages":[],"variants":["ViCoS Towel Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/keypoint-detection-on-vicos-towel-dataset","task":"Keypoint Detection","dataset_variant":"ViCoS Towel Dataset","rows":9,"metrics":["Best F1"],"first_row_in_archive_order":{"model":"CeDiRNet-3DoF - RGB-D (ConvNext-B)","paper":"/paper/center-direction-network-for-grasping-point","metrics":{"Best F1":"81.4"},"code_links":[{"title":"vicoslab/cedirnet-3dof","url":"https://github.com/vicoslab/cedirnet-3dof"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/center-direction-network-for-grasping-point","title":"Center Direction Network for Grasping Point Localization on Cloths","date":"2024-08-26","rows_on_this_dataset":9,"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."}