{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:37:24Z","timestamp":1786534644322,"version":"3.56.0"},"reference-count":60,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Creating realistic 3D human\u2010human interactions in virtual environments is challenging due to the high degrees of freedom in human body and the need for physically accurate poses that do not collide with each other. Traditional methods for humanhuman interaction are based on motion tracking or 3D body reconstruction, but lack generative capabilities. Recent generative methods enable the synthesis of individual or interacting motions via text or image input, but generally fall short in modeling close interactions. This paper introduces a novel generative model for close 3D human\u2010human interactions using a conditional variational autoencoder (cVAE), which generates poses for one human conditioned on the pose of another, allowing for controlled and diverse interaction synthesis. To train our model, we address two underlying long\u2010standing challenges in the field of human\u2010human interaction: data scarcity, for which we propose an automated supervised data augmentation strategy that generates synthetic yet realistic interaction poses; and collision awareness in generative approaches, for which we propose a self\u2010supervised loss based on a collision resolution technique using volumetric proxies to ensure physically correct interactions. We extensively evaluate the capabilities of our model, and demonstrate a wide variety of plausible and physically correct interactions, not possible to generate with current state\u2010of\u2010the\u2010art methods.<\/jats:p>","DOI":"10.1111\/cgf.70561","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:04:41Z","timestamp":1786532681000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GNOCHI: Generative Neural mOdel for Close Human\u2010Human Interactions"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1309-8383","authenticated-orcid":false,"given":"Gonzalo","family":"G\u00f3mez\u2010Nogales","sequence":"first","affiliation":[{"name":"Universidad Rey Juan Carlos  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5621-7565","authenticated-orcid":false,"given":"Marc","family":"Comino\u2010Trinidad","sequence":"additional","affiliation":[{"name":"Universidad Rey Juan Carlos  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0021-3930","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Casado\u2010Elvira","sequence":"additional","affiliation":[{"name":"Universidad Rey Juan Carlos  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-089X","authenticated-orcid":false,"given":"Dan","family":"Casas","sequence":"additional","affiliation":[{"name":"Universidad Rey Juan Carlos  Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"e_1_2_8_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"e_1_2_8_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242152"},{"key":"e_1_2_8_4_2","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-031-73242-3_6","volume-title":"Computer Vision \u2013 ECCV 2024","author":"Fan K.","year":"2025"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"e_1_2_8_6_2","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Fieraru M.","year":"2021"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"e_1_2_8_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00072"},{"issue":"10","key":"e_1_2_8_9_2","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1109\/TVCG.2015.2459687","article-title":"Optimization integrator for large time steps","volume":"21","author":"Gast T. F.","year":"2015","journal-title":"IEEE transactions on visualization and computer graphics"},{"key":"e_1_2_8_10_2","doi-asserted-by":"crossref","unstructured":"GhoshA. ZhouB. DabralR. WangJ. GolyanikV. TheobaltC. SlusallekP. GuoC.: DuetGen: Music Driven Two\u2010Person Dance Generation via Hierarchical Masked Modeling. InACM SIGGRAPH Conference Proceedings(2025). 3","DOI":"10.1145\/3721238.3730741"},{"key":"e_1_2_8_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"e_1_2_8_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"e_1_2_8_13_2","volume-title":"ACM SIGGRAPH 2010 Papers","author":"Ho E. S. L.","year":"2010"},{"key":"e_1_2_8_13_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/1833349.1778770. 3","DOI":"10.1145\/1833349.1778770"},{"key":"e_1_2_8_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"e_1_2_8_15_2","first-page":"1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Javed M. G.","year":"2025"},{"key":"e_1_2_8_16_2","doi-asserted-by":"crossref","unstructured":"JiangZ. GuoC. KaufmannM. JiangT. ValentinJ. HilligesO. SongJ.: Multiply: Reconstruction of multiple people from monocular video in the wild. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2024). 3","DOI":"10.1109\/CVPR52733.2024.00019"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"e_1_2_8_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"e_1_2_8_19_2","first-page":"117","volume-title":"Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation","author":"Kim M.","year":"2012"},{"issue":"10","key":"e_1_2_8_20_2","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1002\/1097-0207(20001210)49:10<1295::AID-NME993>3.0.CO;2-W","article-title":"Variational integrators and the newmark algorithm for conservative and dissipative mechanical systems","volume":"49","author":"Kane C.","year":"2000","journal-title":"International Journal for Numerical Methods in Engineering"},{"key":"e_1_2_8_21_2","unstructured":"LabsB. F.:Flux.https:\/\/github.com\/black-forest-labs\/flux 2024. 8"},{"key":"e_1_2_8_22_2","doi-asserted-by":"crossref","unstructured":"LiuS. GuoC. ZhouB. WangJ.: Ponimator: Unfolding interactive pose for versatile human\u2010human interaction animation. InICCV(2025). 3","DOI":"10.1109\/ICCV51701.2025.01122"},{"key":"e_1_2_8_23_2","first-page":"215","volume-title":"Proceedings of the 2006 ACM SIGGRAPH\/Eurographics Symposium on Computer Animation","author":"Liu C. K.","year":"2006"},{"key":"e_1_2_8_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_8_24_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/2816795.2818013. 2 5","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_8_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"e_1_2_8_25_3","unstructured":"doi:10.1007\/s11263\u2010024\u201002042\u20106. 2"},{"key":"e_1_2_8_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"e_1_2_8_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02044"},{"key":"e_1_2_8_28_2","unstructured":"MalulekeV. H. M\u00fcllerL. RajasegaranJ. PavlakosG. GinosarS. KanazawaA. MalikJ.: Synergy and synchrony in couple dances.arXiv preprint arXiv:2409.04440 abs\/2409.04440(2024) 1\u201311. URL:https:\/\/arxiv.org\/abs\/2409.04440 doi:10.48550\/arXiv.2409.04440. 2"},{"key":"e_1_2_8_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01285"},{"key":"e_1_2_8_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00925"},{"key":"e_1_2_8_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_2_8_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"e_1_2_8_34_2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/978-3-031-73650-6_5","volume-title":"Computer Vision \u2013 ECCV 2024","author":"Shan M.","year":"2025"},{"key":"e_1_2_8_35_2","first-page":"65","volume-title":"Proceedings of the 13th ACM Symposium on Virtual Reality Software and Technology (VRST)","author":"Shum H. P. H.","year":"2007"},{"key":"e_1_2_8_35_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/1315184.1315194. 3","DOI":"10.1145\/1315184.1315194"},{"key":"e_1_2_8_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.257"},{"key":"e_1_2_8_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"e_1_2_8_38_2","first-page":"3483","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems \u2010 2","author":"Sohn K.","year":"2015"},{"key":"e_1_2_8_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3618336"},{"key":"e_1_2_8_39_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3618336. 3","DOI":"10.1145\/3618336"},{"key":"e_1_2_8_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"e_1_2_8_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"e_1_2_8_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00226"},{"key":"e_1_2_8_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661271"},{"key":"e_1_2_8_43_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/2661229.2661271. 3","DOI":"10.1145\/2661229.2661271"},{"key":"e_1_2_8_44_2","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-3-031-20086-1_8","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part II","author":"Xie X.","year":"2022"},{"key":"e_1_2_8_44_3","unstructured":"doi:10.1007\/978\u20103\u2010031\u201020086\u20101_8. 2"},{"key":"e_1_2_8_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"e_1_2_8_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"e_1_2_8_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00187"},{"key":"e_1_2_8_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"e_1_2_8_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"e_1_2_8_50_2","volume-title":"ACM SIGGRAPH 2023 Conference Proceedings","author":"Zhang Y.","year":"2023"},{"key":"e_1_2_8_50_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3588432.3591491. 3 10","DOI":"10.1145\/3588432.3591491"},{"key":"e_1_2_8_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00618"},{"key":"e_1_2_8_52_2","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/978-3-031-20068-7_18","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Zhao K.","year":"2022"},{"key":"e_1_2_8_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70561","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70561","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:04:47Z","timestamp":1786532687000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":60,"alternative-id":["10.1111\/cgf.70561"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70561","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"assertion":[{"value":"2026-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70561"}}