{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T18:50:26Z","timestamp":1774637426425,"version":"3.50.1"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62220106003"],"award-info":[{"award-number":["62220106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["623B2057"],"award-info":[{"award-number":["623B2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:p>\n                    The rapid evolution of 3D content creation, encompassing both AI-powered methods and traditional workflows, is driving an unprecedented demand for automated rigging solutions that can keep pace with the increasing complexity and diversity of 3D models. We introduce\n                    <jats:italic toggle=\"yes\">UniRig<\/jats:italic>\n                    , a novel, unified framework for automatic skeletal rigging that leverages the power of large autoregressive models and a bone-point cross-attention mechanism to generate both high-quality skeletons and skinning weights. Unlike previous methods that struggle with complex or non-standard topologies,\n                    <jats:italic toggle=\"yes\">UniRig<\/jats:italic>\n                    accurately predicts topologically valid skeleton structures thanks to a new\n                    <jats:italic toggle=\"yes\">Skeleton Tree Tokenization<\/jats:italic>\n                    method that efficiently encodes hierarchical relationships within the skeleton. To train and evaluate UniRig, we present\n                    <jats:italic toggle=\"yes\">Rig-XL<\/jats:italic>\n                    , a new large-scale dataset of over 14,000 rigged 3D models spanning a wide range of categories.\n                    <jats:italic toggle=\"yes\">UniRig<\/jats:italic>\n                    significantly outperforms state-of-the-art academic and commercial methods, achieving a 215% improvement in rigging accuracy and a 194% improvement in motion accuracy on challenging datasets. Our method works seamlessly across diverse object categories, from detailed anime characters to complex organic and inorganic structures, demonstrating its versatility and robustness. By automating the tedious and time-consuming rigging process,\n                    <jats:italic toggle=\"yes\">UniRig<\/jats:italic>\n                    has the potential to speed up animation pipelines with unprecedented ease and efficiency. Project Page: https:\/\/zjp-shadow.github.io\/works\/UniRig\/\n                  <\/jats:p>","DOI":"10.1145\/3730930","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T04:02:22Z","timestamp":1753588942000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["One Model to Rig Them All: Diverse Skeleton Rigging with UniRig"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9502-9484","authenticated-orcid":false,"given":"Jia-Peng","family":"Zhang","sequence":"first","affiliation":[{"name":"CS Dept, Tsinghua University, BEIJING, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4483-2751","authenticated-orcid":false,"given":"Cheng-Feng","family":"Pu","sequence":"additional","affiliation":[{"name":"CS Dept, Tsinghua University, BEIJING, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4128-4594","authenticated-orcid":false,"given":"Meng-Hao","family":"Guo","sequence":"additional","affiliation":[{"name":"CS Dept, Tsinghua University, BEIJING, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-4374","authenticated-orcid":false,"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"VAST, BEIJING, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7507-6542","authenticated-orcid":false,"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"CS Dept, Tsinghua University, BEIJING, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Neural jacobian fields: Learning intrinsic mappings of arbitrary meshes. arXiv preprint arXiv:2205.02904","author":"Aigerman Noam","year":"2022","unstructured":"Noam Aigerman, Kunal Gupta, Vladimir G Kim, Siddhartha Chaudhuri, Jun Saito, and Thibault Groueix. 2022. Neural jacobian fields: Learning intrinsic mappings of arbitrary meshes. arXiv preprint arXiv:2205.02904 (2022)."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/276884.276889"},{"key":"e_1_2_2_3_1","unstructured":"Anything-World. 2024. Animation and automated rigging. www.anythingworld.com."},{"key":"e_1_2_2_4_1","unstructured":"Auto-Rig. 2024. Free Auto Rig for any 3D Character | AccuRIG. https:\/\/actorcore.reallusion.com\/accurig."},{"key":"e_1_2_2_5_1","volume-title":"Automatic rigging and animation of 3d characters. ACM Transactions on graphics (TOG) 26, 3","author":"Baran Ilya","year":"2007","unstructured":"Ilya Baran and Jovan Popovi\u0107. 2007. Automatic rigging and animation of 3d characters. ACM Transactions on graphics (TOG) 26, 3 (2007), 72\u2013es."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2643042"},{"key":"e_1_2_2_7_1","volume-title":"Blender - a 3D modelling and rendering package","unstructured":"Blender. 2018. Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam. http:\/\/www.blender.org"},{"key":"e_1_2_2_8_1","unstructured":"Yiwen Chen Tong He Di Huang Weicai Ye Sijin Chen Jiaxiang Tang Xin Chen Zhongang Cai Lei Yang Gang Yu et al. 2024. MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers. arXiv preprint arXiv:2406.10163 (2024)."},{"key":"e_1_2_2_9_1","volume-title":"HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset. arXiv preprint arXiv:2412.02317","author":"Chu Zedong","year":"2024","unstructured":"Zedong Chu, Feng Xiong, Meiduo Liu, Jinzhi Zhang, Mingqi Shao, Zhaoxu Sun, Di Wang, and Mu Xu. 2024. HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset. arXiv preprint arXiv:2412.02317 (2024)."},{"key":"e_1_2_2_10_1","volume-title":"Samir Yitzhak Gadre, et al","author":"Deitke Matt","year":"2024","unstructured":"Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, et al. 2024. Objaverse-xl: A universe of 10m+ 3d objects. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485895.2485919"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.54501\/jots.v1i1.24"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_15"},{"key":"e_1_2_2_14_1","volume-title":"Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale. arXiv preprint arXiv:2412.09548","author":"Hao Zekun","year":"2024","unstructured":"Zekun Hao, David W Romero, Tsung-Yi Lin, and Ming-Yu Liu. 2024. Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale. arXiv preprint arXiv:2412.09548 (2024)."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"e_1_2_2_16_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Nozomi Isozaki Shigeyoshi Ishima Yusuke Yamada Yutaka Obuchi Rika Sato and Norio Shimizu. 2021. VRoid studio: a tool for making anime-like 3D characters using your imagination. In SIGGRAPH Asia 2021 Real-Time Live! 1\u20131.","DOI":"10.1145\/3478511.3491311"},{"key":"e_1_2_2_18_1","first-page":"1","article-title":"Learning skeletal articulations with neural blend shapes","volume":"40","author":"Li Peizhuo","year":"2021","unstructured":"Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, and Baoquan Chen. 2021. Learning skeletal articulations with neural blend shapes. ACM Transactions on Graphics (TOG) 40, 4 (2021), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0344-6"},{"key":"e_1_2_2_20_1","volume-title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models. arXiv preprint arXiv:2405.16645","author":"Liang Hanwen","year":"2024","unstructured":"Hanwen Liang, Yuyang Yin, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N Plataniotis, Yao Zhao, and Yunchao Wei. 2024. Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models. arXiv preprint arXiv:2405.16645 (2024)."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_37"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356495"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_2_2_24_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.05.018"},{"key":"e_1_2_2_26_1","series-title":"Series B. Biological Sciences 200, 1140","volume-title":"Representation and recognition of the spatial organization of three-dimensional shapes. Proceedings of the Royal Society of London","author":"Marr David","year":"1978","unstructured":"David Marr and Herbert Keith Nishihara. 1978. Representation and recognition of the spatial organization of three-dimensional shapes. Proceedings of the Royal Society of London. Series B. Biological Sciences 200, 1140 (1978), 269\u2013294."},{"key":"e_1_2_2_27_1","unstructured":"Meshy. 2024. Meshy - convert text and images to 3D models. https:\/\/www.meshy.com."},{"key":"e_1_2_2_28_1","unstructured":"Models-Resource. 2019. The Models-Resource."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658217"},{"key":"e_1_2_2_30_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0324-2"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"e_1_2_2_33_1","volume-title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters. arXiv preprint arXiv:2411.17423","author":"Sun Mingze","year":"2024","unstructured":"Mingze Sun, Junhao Chen, Junting Dong, Yurun Chen, Xinyu Jiang, Shiwei Mao, Puhua Jiang, Jingbo Wang, Bo Dai, and Ruqi Huang. 2024. DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters. arXiv preprint arXiv:2411.17423 (2024)."},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1576246.1531377"},{"key":"e_1_2_2_35_1","volume-title":"Warudo: Interactive and Accessible Live Performance Capture. In ACM SIGGRAPH 2024 Real-Time Live! 1\u20132.","author":"Tang Man To","year":"2024","unstructured":"Man To Tang and Jesse Thompson. 2024. Warudo: Interactive and Accessible Live Performance Capture. In ACM SIGGRAPH 2024 Real-Time Live! 1\u20132."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2320500"},{"key":"e_1_2_2_37_1","unstructured":"VAST. 2025. Tripo AI. https:\/\/www.tripoai.com."},{"key":"e_1_2_2_38_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_2_2_39_1","volume-title":"Hmc: Hierarchical mesh coarsening for skeleton-free motion retargeting. arXiv preprint arXiv:2303.10941","author":"Wang Haoyu","year":"2023","unstructured":"Haoyu Wang, Shaoli Huang, Fang Zhao, Chun Yuan, and Ying Shan. 2023a. Hmc: Hierarchical mesh coarsening for skeleton-free motion retargeting. arXiv preprint arXiv:2303.10941 (2023)."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00841"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00587"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_3"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"e_1_2_2_44_1","volume-title":"Rignet: Neural rigging for articulated characters. arXiv preprint arXiv:2005.00559","author":"Xu Zhan","year":"2020","unstructured":"Zhan Xu, Yang Zhou, Evangelos Kalogerakis, Chris Landreth, and Karan Singh. 2020. Rignet: Neural rigging for articulated characters. arXiv preprint arXiv:2005.00559 (2020)."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00041"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555390"},{"key":"e_1_2_2_47_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201396","article-title":"Voxel cores: Efficient, robust, and provably good approximation of 3d medial axes","volume":"37","author":"Yan Yajie","year":"2018","unstructured":"Yajie Yan, David Letscher, and Tao Ju. 2018. Voxel cores: Efficient, robust, and provably good approximation of 3d medial axes. ACM Transactions on Graphics (TOG) 37, 4 (2018), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980241"},{"key":"e_1_2_2_49_1","volume-title":"Sampart3d: Segment any part in 3d objects. arXiv preprint arXiv:2411.07184","author":"Yang Yunhan","year":"2024","unstructured":"Yunhan Yang, Yukun Huang, Yuan-Chen Guo, Liangjun Lu, Xiaoyang Wu, Edmund Y Lam, Yan-Pei Cao, and Xihui Liu. 2024. Sampart3d: Segment any part in 3d objects. arXiv preprint arXiv:2411.07184 (2024)."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687909"},{"key":"e_1_2_2_51_1","volume-title":"Mesh2Animation: Unsupervised Animating for Quadruped 3D Objects","author":"Yu Zhenbo","year":"2025","unstructured":"Zhenbo Yu, Junjie Wang, Hang Wang, Zhiyuan Zhang, Jinxian Liu, Zefan Li, Bingbing Ni, and Wenjun Zhang. 2025. Mesh2Animation: Unsupervised Animating for Quadruped 3D Objects. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"e_1_2_2_53_1","volume-title":"TapMo: Shape-aware Motion Generation of Skeleton-free Characters. arXiv preprint arXiv:2310.12678","author":"Zhang Jiaxu","year":"2023","unstructured":"Jiaxu Zhang, Shaoli Huang, Zhigang Tu, Xin Chen, Xiaohang Zhan, Gang Yu, and Ying Shan. 2023a. TapMo: Shape-aware Motion Generation of Skeleton-free Characters. arXiv preprint arXiv:2310.12678 (2023)."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3423426"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"e_1_2_2_56_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3730930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:50:35Z","timestamp":1774633835000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3730930"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":56,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,1]]}},"alternative-id":["10.1145\/3730930"],"URL":"https:\/\/doi.org\/10.1145\/3730930","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-01-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}