{"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/contactdb-analyzing-and-predicting-grasp","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","arxiv_id":"1904.06830","date":"2019-04-15","proceeding":"CVPR 2019 6","authors":["Samarth Brahmbhatt","Cusuh Ham","Charles C. Kemp","James Hays"],"abstract":"Grasping and manipulating objects is an important human skill. Since\nhand-object contact is fundamental to grasping, capturing it can lead to\nimportant insights. However, observing contact through external sensors is\nchallenging because of occlusion and the complexity of the human hand. We\npresent ContactDB, a novel dataset of contact maps for household objects that\ncaptures the rich hand-object contact that occurs during grasping, enabled by\nuse of a thermal camera. Participants in our study grasped 3D printed objects\nwith a post-grasp functional intent. ContactDB includes 3750 3D meshes of 50\nhousehold objects textured with contact maps and 375K frames of synchronized\nRGB-D+thermal images. To the best of our knowledge, this is the first\nlarge-scale dataset that records detailed contact maps for human grasps.\nAnalysis of this data shows the influence of functional intent and object size\non grasping, the tendency to touch/avoid 'active areas', and the high frequency\nof palm and proximal finger contact. Finally, we train state-of-the-art image\ntranslation and 3D convolution algorithms to predict diverse contact patterns\nfrom object shape. Data, code and models are available at\nhttps://contactdb.cc.gatech.edu.","url_abs":"http://arxiv.org/abs/1904.06830v1","url_pdf":"http://arxiv.org/pdf/1904.06830v1.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":"contactdb-analyzing-and-predicting-grasp","repo_url":"https://github.com/samarth-robo/contactdb_prediction","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"contactdb-analyzing-and-predicting-grasp","repo_url":"https://github.com/samarth-robo/contactdb_utils","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"human-grasp-contact-prediction","task_name":"Grasp Contact Prediction"},{"task_slug":"object","task_name":"Object"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[{"slug":"contactdb","name":"ContactDB","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-grasp-contact-prediction-on-contactdb","task":"Grasp Contact Prediction","dataset":"ContactDB","model":"DiverseNet-VoxNet","rank_in_archive_order":1,"of":4,"metrics":{"Error rate":"8.72"},"uses_additional_data":false},{"leaderboard":"/sota/human-grasp-contact-prediction-on-contactdb","task":"Grasp Contact Prediction","dataset":"ContactDB","model":"sMCL-VoxNet","rank_in_archive_order":2,"of":4,"metrics":{"Error rate":"17.27"},"uses_additional_data":false},{"leaderboard":"/sota/human-grasp-contact-prediction-on-contactdb","task":"Grasp Contact Prediction","dataset":"ContactDB","model":"DiverseNet-PointNet","rank_in_archive_order":3,"of":4,"metrics":{"Error rate":"21.82"},"uses_additional_data":false},{"leaderboard":"/sota/human-grasp-contact-prediction-on-contactdb","task":"Grasp Contact Prediction","dataset":"ContactDB","model":"sMCL-PointNet","rank_in_archive_order":4,"of":4,"metrics":{"Error rate":"29.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.06830","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}