{"id":2459,"date":"2025-06-01T09:00:00","date_gmt":"2025-06-01T09:00:00","guid":{"rendered":"https:\/\/wp.lancs.ac.uk\/icvl\/?p=2459"},"modified":"2025-07-30T06:46:34","modified_gmt":"2025-07-30T06:46:34","slug":"3d-points-splatting-for-real-time-dynamic-hand-reconstruction","status":"publish","type":"post","link":"http:\/\/wp.lancs.ac.uk\/icvl\/2025\/06\/01\/3d-points-splatting-for-real-time-dynamic-hand-reconstruction\/","title":{"rendered":"3D Points Splatting for Real-Time Dynamic Hand Reconstruction"},"content":{"rendered":"\n

3D Points Splatting for Real-Time Dynamic Hand Reconstruction<\/h1>\n\n\n\n

Zheheng Jiang1<\/sup>, Hossein Rahmani2<\/sup>, Sue Black3<\/sup>, and Bryan M. Williams2<\/sup><\/p>\n\n\n\n

1 <\/sup>School of Computing and Mathematical Science, University of Leicester, Leicester, UK
1 <\/sup>School of Computing and Communications, Lancaster University, Lancaster, UK
2<\/sup> St John\u2019s College of the University of Oxford, Oxford, UK<\/p>\n\n\n\n

\n
Paper<\/a><\/div>\n\n\n\n
PDF<\/a><\/div>\n\n\n\n
Contact<\/a><\/div>\n<\/div>\n\n\n\n

Abstract<\/h2>\n\n\n\n

We present 3D Points Splatting Hand Reconstruction (3D-PSHR), a real-time and photo-realistic hand reconstruction approach. We propose a self-adaptive canonical points upsampling strategy to achieve high-resolution hand geometry representation. This is followed by a self-adaptive deformation that deforms the hand from the canonical space to the target pose, adapting to the dynamic changing of canonical points which, in contrast to the common practice of subdividing the MANO model, offers greater flexibility and results in improved geometry fitting. To model texture, we disentangle the appearance color into the intrinsic albedo and pose-aware shading, which are learned through a Context-Attention module. Moreover, our approach allows the geometric and the appearance models to be trained simultaneously in an end-to-end manner. We demonstrate that our method is capable of producing animatable, photorealistic and relightable hand reconstructions using multiple datasets, including monocular videos captured with handheld smartphones and large-scale multi-view videos featuring various hand poses. We also demonstrate that our approach achieves real-time rendering speeds while simultaneously maintaining superior performance compared to existing state-of-the-art methods.<\/p>\n\n\n\n

Authors<\/h2>\n\n\n\n
\n
\"\"
Dr Zheheng Jiang<\/figcaption><\/figure>\n\n\n\n
\"\"
Dr Hossein Rahmani<\/figcaption><\/figure>\n\n\n\n
\"\"
Prof Lady Sue Black<\/figcaption><\/figure>\n\n\n\n
\"\"
Dr Bryan M. Williams<\/figcaption><\/figure>\n<\/figure>\n\n\n\n

Keywords<\/h2>\n\n\n\n

High-resolution hand geometry; Intrinsic albedo; Pose-aware shading; Real-time rendering<\/p>\n\n\n\n

Citation<\/h2>\n\n\n\n

Jiang Z, Rahmani H, Black S, Williams BM. 3D Points Splatting for Real-Time Dynamic Hand Reconstruction. Pattern Recognition. 2025; 162:111426.<\/p>\n\n\n\n

Also available as Jiang Z, Rahmani H, Black S, Williams BM. 3D Points Splatting for Real-Time Dynamic Hand Reconstruction. arXiv preprint arXiv:2312.13770. 2023 Dec 21.<\/p>\n\n\n\n

@article{jiang20253d,
title={3d points splatting for real-time dynamic hand reconstruction},
author={Jiang, Zheheng and Rahmani, Hossein and Black, Sue and Williams, Bryan},
journal={Pattern Recognition},
volume={162},
pages={111426},
year={2025},
publisher={Elsevier}
}<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
Jiang Z, Rahmani H, Black S, Williams BM. Pattern Recognition. 2025; 162:111426.<\/p>\n","protected":false},"author":1442,"featured_media":2461,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[12,7],"tags":[141,21,23,22,29,46,31,42,45],"class_list":["post-2459","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-journal-paper","category-publication","tag-141","tag-biometrics","tag-bryan-m-williams","tag-deep-learning","tag-h-unique","tag-hossein-rahmani","tag-machine-learning","tag-sue-black","tag-zheheng-jiang"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/wp.lancs.ac.uk\/icvl\/files\/2024\/04\/Jiang233D.png?fit=848%2C675","jetpack-related-posts":[],"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/posts\/2459","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/users\/1442"}],"replies":[{"embeddable":true,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/comments?post=2459"}],"version-history":[{"count":11,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/posts\/2459\/revisions"}],"predecessor-version":[{"id":2873,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/posts\/2459\/revisions\/2873"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/media\/2461"}],"wp:attachment":[{"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/media?parent=2459"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/categories?post=2459"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/wp.lancs.ac.uk\/icvl\/wp-json\/wp\/v2\/tags?post=2459"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}