{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:47:48Z","timestamp":1753890468870,"version":"3.41.2"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T00:00:00Z","timestamp":1744329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>Motion synthesis using machine learning has seen rapid advancements in recent years. Unlike traditional animation methods, utilizing deep learning to generate human movement offers the unique advantage of producing slight variations between motions, similar to the natural variability observed in real examples. While several motion synthesis methods have achieved remarkable success in generating highly varied and probabilistic animations, controlling the synthesized animation in real-time while retaining stochastic elements remains a serious challenge. The main purpose of this work is to develop a Conditional Generative Adversarial Network to generate real-time controlled motion that balances realism and stochastic variability. To achieve this, three novel Generative Adversarial models were developed. The models differ in the architecture of their generators that utilize: a Mixture-of-Experts method, a Latent-Modulated Noise Injection technique, and a Transformer-based architecture respectively. We consider the latter to be the main contribution of this work, and we evaluate our method by comparing it to the other models on both stylized locomotion data and complex, aperiodic dance sequences, assessing its ability to generate diverse, realistic motions, being able to mix between different styles while responding to motion control. Our findings highlight the trade-offs between motion quality, variety and motion generalization in real-time synthesis by comparing by exploring the advantages and disadvantages of each architecture, contributing to the ongoing development of more flexible and varied animation techniques.<\/jats:p>","DOI":"10.3389\/fcomp.2025.1549693","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T05:15:06Z","timestamp":1744348506000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Advanced articulated motion prediction"],"prefix":"10.3389","volume":"7","author":[{"given":"Anthony","family":"Belessis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iliana","family":"Loi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Moustakas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3519","DOI":"10.1109\/TVCG.2022.3163676","article-title":"Rhythm is a dancer: music-driven motion synthesis with global structure","volume":"29","author":"Aristidou","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graph"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534373","article-title":"\u201cEvaluation of generative adversarial networks for time series data,\u201d","author":"Arnout","year":"2021","journal-title":"2021 International Joint Conference on Neural Networks (IJCNN)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"B4","doi-asserted-by":"publisher","first-page":"723","DOI":"10.48550\/arXiv.0805.2368","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res"},{"year":"2014","author":"Haas","journal-title":"A History of the Unity Game Engine.","key":"B5"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118","article-title":"\u201cStochastic scene-aware motion prediction,\u201d","author":"Hassan","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417836","article-title":"Moglow: probabilistic and controllable motion synthesis using normalising flows","volume":"39","author":"Henter","year":"2020","journal-title":"ACM Trans. Graph"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3073663","DOI":"10.1145\/3072959.3073663","article-title":"Phase-functioned neural networks for character control","volume":"36","author":"Holden","year":"2017","journal-title":"ACM Trans. Graph"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453","article-title":"\u201cA style-based generator architecture for generative adversarial networks,\u201d","author":"Karras","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205","article-title":"\u201cGuided motion diffusion for controllable human motion synthesis,\u201d","author":"Karunratanakul","year":"2023","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"B11","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR, abs\/1412.6980"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00096","article-title":"\u201cNifty: neural object interaction fields for guided human motion synthesis,\u201d","author":"Kulkarni","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530157","article-title":"Ganimator: neural motion synthesis from a single sequence","volume":"41","author":"Li","year":"2022","journal-title":"ACM Trans. Graph"},{"key":"B14","doi-asserted-by":"publisher","first-page":"5810","DOI":"10.1109\/TVCG.2023.3308753","article-title":"Machine learning approaches for 3d motion synthesis and musculoskeletal dynamics estimation: a survey","volume":"30","author":"Loi","year":"2023","journal-title":"IEEE Trans. Vis. Comput. Graph"},{"key":"B15","article-title":"Modularity trumps invariance for compositional robustness","author":"Mason","year":"2023","journal-title":"arXiv preprint arXiv:2306.09005"},{"key":"B16","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1016\/j.cag.2021.09.014","article-title":"Gan-based reactive motion synthesis with class-aware discriminators for human\u2013human interaction","volume":"102","author":"Men","year":"2022","journal-title":"Comput. Graph"},{"key":"B17","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv preprint arXiv:1411.1784"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412160","article-title":"\u201cJumps: joints upsampling method for pose sequences,\u201d","author":"Mourot","year":"2021","journal-title":"2020 25th International Conference on Pattern Recognition (ICPR)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1111\/cgf.14426","article-title":"A survey on deep learning for skeleton-based human animation","volume":"41","author":"Mourot","year":"2022","journal-title":"Comput. Graph. Forum"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3530178","DOI":"10.1145\/3528223.3530178","article-title":"Deepphase: periodic autoencoders for learning motion phase manifolds","volume":"41","author":"Starke","year":"2022","journal-title":"ACM Trans. Graph"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3356505","DOI":"10.1145\/3355089.3356505","article-title":"Neural state machine for character-scene interactions","volume":"38","author":"Starke","year":"2019","journal-title":"ACM Trans. Graph"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3392450","DOI":"10.1145\/3386569.3392450","article-title":"Local motion phases for learning multi-contact character movements","volume":"39","author":"Starke","year":"2020","journal-title":"ACM Trans. Graph"},{"key":"B23","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1007\/978-3-642-34234-9_41","article-title":"\u201cDigitization of cypriot folk dances,\u201d","volume-title":"Proceedings of the 4th International Conference on Progress in Cultural Heritage Preservation, EuroMed'12","author":"Stavrakis","year":"2012"},{"key":"B24","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint arXiv:2209.14916"},{"key":"B25","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1549693\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T05:15:10Z","timestamp":1744348510000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1549693\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,11]]},"references-count":25,"alternative-id":["10.3389\/fcomp.2025.1549693"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1549693","relation":{},"ISSN":["2624-9898"],"issn-type":[{"type":"electronic","value":"2624-9898"}],"subject":[],"published":{"date-parts":[[2025,4,11]]},"article-number":"1549693"}}