{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/t-less-an-rgb-d-dataset-for-6d-pose","title":"T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects","arxiv_id":"1701.05498","date":"2017-01-19","proceeding":null,"authors":["Tomas Hodan","Pavel Haluza","Stepan Obdrzalek","Jiri Matas","Manolis Lourakis","Xenophon Zabulis"],"abstract":"We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e.\ntranslation and rotation, of texture-less rigid objects. The dataset features\nthirty industry-relevant objects with no significant texture and no\ndiscriminative color or reflectance properties. The objects exhibit symmetries\nand mutual similarities in shape and/or size. Compared to other datasets, a\nunique property is that some of the objects are parts of others. The dataset\nincludes training and test images that were captured with three synchronized\nsensors, specifically a structured-light and a time-of-flight RGB-D sensor and\na high-resolution RGB camera. There are approximately 39K training and 10K test\nimages from each sensor. Additionally, two types of 3D models are provided for\neach object, i.e. a manually created CAD model and a semi-automatically\nreconstructed one. Training images depict individual objects against a black\nbackground. Test images originate from twenty test scenes having varying\ncomplexity, which increases from simple scenes with several isolated objects to\nvery challenging ones with multiple instances of several objects and with a\nhigh amount of clutter and occlusion. The images were captured from a\nsystematically sampled view sphere around the object/scene, and are annotated\nwith accurate ground truth 6D poses of all modeled objects. Initial evaluation\nresults indicate that the state of the art in 6D object pose estimation has\nample room for improvement, especially in difficult cases with significant\nocclusion. The T-LESS dataset is available online at cmp.felk.cvut.cz/t-less.","url_abs":"http://arxiv.org/abs/1701.05498v1","url_pdf":"http://arxiv.org/pdf/1701.05498v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"t-less-an-rgb-d-dataset-for-6d-pose","repo_url":"https://github.com/thodan/t-less_toolkit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"t-less-an-rgb-d-dataset-for-6d-pose","repo_url":"https://github.com/thodan/bop_toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"6d-pose-estimation","task_name":"6D Pose Estimation using RGB"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"t-less","name":"T-LESS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1701.05498","atlas_url":"https://app.syntology.ai/?focus=1701.05498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}