PERGAMO: Personalized 3D Garments from Monocular Video
This work addresses the challenge of creating personalized 3D garment animations for digital humans, offering a more efficient and realistic alternative to physics-based simulations, though it appears incremental as it builds on existing data-driven approaches.
The paper tackles the problem of animating 3D garments from monocular video by addressing high computational costs and simulation-to-real gaps, proposing PERGAMO, a data-driven method that learns deformable models to produce animations matching real-world behavior and generalizing to unseen motions.
Clothing 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 development; 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 behaviour, and generalizes to unseen body motions extracted from motion capture dataset.