{"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/learning-to-estimate-3d-hand-pose-from-single","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","arxiv_id":"1705.01389","date":"2017-05-03","proceeding":"ICCV 2017 10","authors":["Christian Zimmermann","Thomas Brox"],"abstract":"Low-cost consumer depth cameras and deep learning have enabled reasonable 3D\nhand pose estimation from single depth images. In this paper, we present an\napproach that estimates 3D hand pose from regular RGB images. This task has far\nmore ambiguities due to the missing depth information. To this end, we propose\na deep network that learns a network-implicit 3D articulation prior. Together\nwith detected keypoints in the images, this network yields good estimates of\nthe 3D pose. We introduce a large scale 3D hand pose dataset based on synthetic\nhand models for training the involved networks. Experiments on a variety of\ntest sets, including one on sign language recognition, demonstrate the\nfeasibility of 3D hand pose estimation on single color images.","url_abs":"http://arxiv.org/abs/1705.01389v3","url_pdf":"http://arxiv.org/pdf/1705.01389v3.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":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/lmb-freiburg/hand3d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/Chenzhoujia/190916-hand3d-CNN-GNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/ajdillhoff/colorhandpose3d-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/bnestor/second-hand-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/theerapatkitti/hand_mask_rcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/theone1984/hand-gesture-ai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/zhong110020/hand3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-to-estimate-3d-hand-pose-from-single","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"sign-language-recognition","task_name":"Sign Language Recognition"}],"methods":[],"datasets_introduced":[{"slug":"rhd","name":"RHD","full_name":"Rendered Hand Pose"},{"slug":"rendered-handpose-dataset","name":"Rendered Handpose Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.01389","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}