GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation
This addresses the challenge of creating physically plausible and editable 3D garments for applications in fashion, virtual try-on, and digital content creation, representing a strong specific gain rather than a foundational advance.
The paper tackles the problem of generating diverse, high-fidelity 3D garments from a single image by introducing GarmentX, a framework that uses a structured parametric representation and an autoregressive model to produce valid, simulation-ready garments, achieving state-of-the-art performance in geometric fidelity and image alignment.
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.