{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T04:45:26Z","timestamp":1777869926692,"version":"3.51.4"},"reference-count":46,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100013348","name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013348","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Facial animation is one of the most labor\u2010intensive aspects of animation and VFX, as traditional rigging consumes weeks of expert time and forces animators to spend countless hours manipulating hundreds of controls to achieve varied expressions. This technical complexity creates a barrier between artistic vision and execution, limiting creative exploration and iteration. In this paper, we introduce\n                    <jats:italic>CANRig<\/jats:italic>\n                    , a fully automated neural facial rigging approach that simplifies the process of creating and editing facial poses by benefiting from global correlations learned from data. Unlike existing neural face models that either sacrifice local control or demand extensive manual region setup, our method introduces continuous local control through a novel conditioning mechanism that operates on a variable region. By modeling deformation as cross\u2010attention between control handles and mesh vertices\u2014modulated by a user\u2010defined region\u2014we enable seamless transitions from precise local adjustments to broad global changes. We further expand our method with a shape\u2010preserving workflow that enables iterative edits, guaranteeing that changes remain untouched even as controls are reconfigured. Our method delivers the best of both worlds: the automation and naturalness of neural methods with the granular control that professional animators demand, and we demonstrate its effectiveness across multiple applications in both animation and high\u2010end visual effects pipelines.\n                  <\/jats:p>","DOI":"10.1111\/cgf.70426","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:00:41Z","timestamp":1777561241000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CANRIG: Cross\u2010Attention Neural Face Rigging with Variable Local Control"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5622-0984","authenticated-orcid":false,"given":"Arad","family":"Mohammadi","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich  Switzerland"},{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4399-3180","authenticated-orcid":false,"given":"Sebastian","family":"Weiss","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3038-4881","authenticated-orcid":false,"given":"Jakob","family":"Buhmann","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2970-4434","authenticated-orcid":false,"given":"Loic","family":"Ciccone","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1909-8082","authenticated-orcid":false,"given":"Robert W.","family":"Sumner","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich  Switzerland"},{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2055-9325","authenticated-orcid":false,"given":"Derek","family":"Bradley","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7496-6185","authenticated-orcid":false,"given":"Martin","family":"Guay","sequence":"additional","affiliation":[{"name":"DisneyResearch|Studios  Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"e_1_2_11_2_2","volume-title":"ACM SIGGRAPH 2024 Talks","author":"Arcelin B.","year":"2024"},{"key":"e_1_2_11_3_2","volume-title":"SIGGRAPH Asia 2023 Conference Papers","author":"Agrawal D.","year":"2023"},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591566"},{"key":"e_1_2_11_5_2","doi-asserted-by":"crossref","unstructured":"BaiZ. CuiZ. RahimJ. A. LiuX. TanP.: Riggable 3D face reconstruction via in-network optimization. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2021) pp.6216\u20136225. 2","DOI":"10.1109\/CVPR46437.2021.00615"},{"issue":"4","key":"e_1_2_11_6_2","doi-asserted-by":"crossref","first-page":"75:1","DOI":"10.1145\/2010324.1964970","article-title":"High-quality passive facial performance capture using anchor frames","volume":"30","author":"Beeler T.","year":"2011","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_7_2","first-page":"187","volume-title":"Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques","author":"Blanz V.","year":"1999"},{"issue":"4","key":"e_1_2_11_8_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530114","article-title":"Local anatomically-constrained facial performance retargeting","volume":"41","author":"Chandran P.","year":"2022","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_9_2","volume-title":"SIGGRAPH Asia 2022 Conference Papers","author":"Choi B.","year":"2022"},{"key":"e_1_2_11_10_2","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/3DV50981.2020.00044","volume-title":"2020 International Conference on 3D Vision (3DV)","author":"Chandran P.","year":"2020"},{"key":"e_1_2_11_11_2","doi-asserted-by":"crossref","unstructured":"ChenC. O'TooleM. BharajG. GarridoP.: Implicit neural head synthesis via controllable local deformation fields. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2023) pp.416\u2013426. 2","DOI":"10.1109\/CVPR52729.2023.00048"},{"issue":"4","key":"e_1_2_11_12_2","doi-asserted-by":"crossref","first-page":"59:1","DOI":"10.1145\/3747866","article-title":"NeuRiPhy: Neural baking of physics-based deformations for facial rigs","volume":"8","author":"Corigliano D.","year":"2025","journal-title":"Proceedings of the ACM on Computer Graphics and Interactive Techniques"},{"issue":"2","key":"e_1_2_11_13_2","doi-asserted-by":"crossref","first-page":"e70009","DOI":"10.1111\/cgf.70009","article-title":"Neural face skinning for mesh-agnostic facial expression cloning","volume":"44","author":"Cha S.","year":"2025","journal-title":"Computer Graphics Forum"},{"issue":"2","key":"e_1_2_11_14_2","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1111\/cgf.14468","article-title":"Shape transformers: Topology-independent 3D shape models using transformers","volume":"41","author":"Chandran P.","year":"2022","journal-title":"Computer Graphics Forum"},{"key":"e_1_2_11_15_2","doi-asserted-by":"crossref","unstructured":"DingZ. ZhangX. XiaZ. JebeL. TuZ. ZhangX.: DiffusionRig: Learning personalized priors for facial appearance editing. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2023) pp.12736\u201312746. 2","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"e_1_2_11_16_2","volume-title":"Facial Action Coding System: A Technique for the Measurement of Facial Movement","author":"Ekman P.","year":"1978"},{"issue":"4","key":"e_1_2_11_17_2","doi-asserted-by":"crossref","first-page":"88:1","DOI":"10.1145\/3450626.3459936","article-title":"Learning an animatable detailed 3D face model from in-the-wild images","volume":"40","author":"Feng Y.","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_18_2","doi-asserted-by":"crossref","unstructured":"GiebenhainS. KirschsteinT. GeorgopoulosM. R\u00fcnzM. AgapitoL. NiessnerM.: Learning neural parametric head models. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2023) pp.21003\u201321012. 2","DOI":"10.1109\/CVPR52729.2023.02012"},{"key":"e_1_2_11_19_2","doi-asserted-by":"crossref","unstructured":"GuoZ. XiangJ. MaK. ZhouW. LiH. ZhangR.: Make-It-Animatable: An efficient framework for authoring animation-ready 3D characters. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2025) pp.10783\u201310792. 2","DOI":"10.1109\/CVPR52734.2025.01007"},{"issue":"3","key":"e_1_2_11_20_2","doi-asserted-by":"crossref","first-page":"28:1","DOI":"10.1145\/2890493","article-title":"Reconstruction of personalized 3D face rigs from monocular video","volume":"35","author":"Garrido P.","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_21_2","volume-title":"Neural Networks: A Comprehensive Foundation","author":"Haykin S.","year":"1994"},{"key":"e_1_2_11_22_2","unstructured":"HendrycksD. GimpelK.: Gaussian error linear units (GELUs).arXiv preprint arXiv:1606.08415(2016). 4 7"},{"key":"e_1_2_11_23_2","unstructured":"KingmaD. P. BaJ.: Adam: A method for stochastic optimization. InProceedings of the 3rd International Conference on Learning Representations (ICLR)(2015). 7"},{"issue":"2","key":"e_1_2_11_24_2","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1111\/cgf.13108","article-title":"Enriching facial blendshape rigs with physical simulation","volume":"36","author":"Kozlov Y.","year":"2017","journal-title":"Computer Graphics Forum"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2010.41"},{"key":"e_1_2_11_26_2","unstructured":"LewisJ. AnjyoK. RheeT. ZhangM. PighinF. DengZ.: Practice and theory of blendshape facial models.Eurographics 2014 - State of the Art Reports(2014). 3"},{"issue":"6","key":"e_1_2_11_27_2","first-page":"194:1","article-title":"Learning a model of facial shape and expression from 4D scans","volume":"36","author":"Li T.","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"1","key":"e_1_2_11_28_2","first-page":"3:1","article-title":"Face poser: Interactive modeling of 3D facial expressions using facial priors","volume":"29","author":"Lau M.","year":"2009","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"4","key":"e_1_2_11_29_2","first-page":"32:1","article-title":"Example-based facial rigging","volume":"29","author":"Li H.","year":"2010","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_30_2","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.neucom.2019.03.082","article-title":"AU R-CNN: Encoding expert prior knowledge into R-CNN for action unit detection","volume":"355","author":"Ma C.","year":"2019","journal-title":"Neurocomputing"},{"issue":"6","key":"e_1_2_11_31_2","doi-asserted-by":"crossref","first-page":"179:1","DOI":"10.1145\/2508363.2508417","article-title":"Sparse localized deformation components","volume":"32","author":"Neumann T.","year":"2013","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_32_2","first-page":"183","volume-title":"Eurographics 2012 - State of the Art Reports","author":"Orvalho V.","year":"2012"},{"key":"e_1_2_11_33_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Potamias R. A.","year":"2024"},{"key":"e_1_2_11_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591556"},{"key":"e_1_2_11_35_2","first-page":"1","volume-title":"ACM SIGGRAPH 2020 Talks","author":"Radzihovsky S.","year":"2020"},{"key":"e_1_2_11_36_2","first-page":"1556","volume-title":"Proceedings of the 29th European Signal Processing Conference (EUSIPCO)","author":"Rackovic S.","year":"2021"},{"key":"e_1_2_11_37_2","unstructured":"RainaP. TaubnerF. TuliM. TehE. W. FerreiraK.: PrismAvatar: Real-time animated 3D neural head avatars on edge devices.arXiv preprint arXiv:2502.07030(2025). 3"},{"issue":"4","key":"e_1_2_11_38_2","first-page":"34:1","article-title":"Accurate face rig approximation with deep differential subspace reconstruction","volume":"39","author":"Song S. L.","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"4","key":"e_1_2_11_39_2","first-page":"76:1","article-title":"Interactive region-based linear 3D face models","volume":"30","author":"Tena J. R.","year":"2011","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_40_2","doi-asserted-by":"crossref","unstructured":"TarasiouM. PotamiasR. A. O'SullivanE. PloumpisS. ZafeiriouS.: Locally adaptive neural 3d morphable models. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(June2024) pp.1867\u20131876. 3","DOI":"10.1109\/CVPR52733.2024.00183"},{"issue":"3","key":"e_1_2_11_41_2","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1145\/1073204.1073209","article-title":"Face transfer with multilinear models","volume":"24","author":"Vlasic D.","year":"2005","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_42_2","first-page":"389","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Vesdapunt N.","year":"2020"},{"issue":"4","key":"e_1_2_11_43_2","first-page":"58:1","article-title":"RigNet: Neural rigging for articulated characters","volume":"39","author":"Xu Z.","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_11_44_2","unstructured":"YanH. LuoK. LiW. LiangY. LiS. HuangJ. GuoC. TanP.: PoseMaster: Generating 3D characters in arbitrary poses from a single image.arXiv preprint arXiv:2506.21076(2025). 2"},{"key":"e_1_2_11_45_2","doi-asserted-by":"crossref","first-page":"131329","DOI":"10.1016\/j.neucom.2025.131329","article-title":"Style-morpheus: Learning a StyleGAN-based 3D-aware morphable face model with a disentangled style space","volume":"654","author":"Yan P.","year":"2025","journal-title":"Neurocomputing"},{"key":"e_1_2_11_46_2","doi-asserted-by":"crossref","unstructured":"ZhaoZ. WengD. GuoH. HouJ. ZhouJ.: Facial auto rigging from 4D expressions via skinning decomposition. InProceedings of the 31st ACM International Conference on Multimedia(2023) pp.6101\u20136109. 3","DOI":"10.1145\/3581783.3612934"},{"key":"e_1_2_11_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3480151"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70426","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70426","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:00:48Z","timestamp":1777561248000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":46,"alternative-id":["10.1111\/cgf.70426"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70426","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"assertion":[{"value":"2026-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70426"}}