Casado-Elvira, AndrésComino Trinidad, MarcCasas, Dan2023-09-272023-09-272023PERGAMO: Personalized 3D Garments from Monocular Video. Andrés Casado-Elvira, Marc Comino Trinidad, Dan Casasformat © 2023 The Authors. Computer Graphics Forum published by Eurographics - The European Association for Computer Graphics and John Wiley & Sons Ltd.https://doi.org/10.1111/cgf.146441467-8659https://hdl.handle.net/10115/24577the Comunidad de Madrid in the framework of the Multiannual Agreement with the Universidad Rey Juan Carlos in line of Action 1, “Encouragement of research for young PhD”. Grant Number: CaptHuRe (M2736) the Universidad Rey Juan Carlos through the Distinguished Researcher position INVESDIST-04. Grant Number: 17/12/2020 Leonardo Fellowship from the Fundación BBVAClothing plays a fundamental role in digital humans. Current approaches to animate 3D garments are mostly based on realistic physics simulation, however, they typically suffer from two main issues: high computational run-time cost, which hinders their deployment; and simulation-to-real gap, which impedes the synthesis of specific real-world cloth samples. To circumvent both issues we propose PERGAMO, a data-driven approach to learn a deformable model for 3D garments from monocular images. To this end, we first introduce a novel method to reconstruct the 3D geometry of garments from a single image, and use it to build a dataset of clothing from monocular videos. We use these 3D reconstructions to train a regression model that accurately predicts how the garment deforms as a function of the underlying body pose. We show that our method is capable of producing garment animations that match the real-world behavior, and generalizes to unseen body motions extracted from motion capture dataset.engAtribución-NoComercial 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc/4.0/Computing methodologiesComputer graphicsNeural networksinfo:eu-repo/semantics/article10.1111/cgf.14644info:eu-repo/semantics/openAccess