This work presents GarmentX, a novel framework for generating diverse, high-fidelity, and wearable 3D garments from a single input image. Traditional garment reconstruction methods directly predict 2D pattern edges and their connectivity, an overly unconstrained approach that often leads to severe self-intersections and physically implausible garment structures. In contrast, GarmentX introduces a structured and editable parametric representation compatible with GarmentCode, ensuring that the decoded sewing patterns always form valid, simulation-ready 3D garments while allowing for intuitive modifications of garment shape and style. To achieve this, we employ a masked autoregressive model that sequentially predicts garment parameters, leveraging autoregressive modeling for structured generation while mitigating inconsistencies in direct pattern prediction. Additionally, we introduce GarmentX dataset, a large-scale dataset of 378,682 garment parameter-image pairs, constructed through an automatic data generation pipeline that synthesizes diverse and high-quality garment images conditioned on parametric garment representations. Through integrating our method with GarmentX dataset, we achieve state-of-the-art performance in geometric fidelity and input image alignment, significantly outperforming prior approaches. We will release GarmentX dataset upon publication.
View on arXiv@article{guo2025_2504.20409,
title={ GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation },
author={ Jingfeng Guo and Jinnan Chen and Weikai Chen and Zhenyu Sun and Lanjiong Li and Baozhu Zhao and Lingting Zhu and Xin Wang and Qi Liu },
journal={arXiv preprint arXiv:2504.20409},
year={ 2025 }
}