GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912353080049664 |
|---|---|
| author | Guo, Jingfeng Chen, Jinnan Chen, Weikai Sun, Zhenyu Li, Lanjiong Zhao, Baozhu Zhu, Lingting Wang, Xin Liu, Qi |
| author_facet | Guo, Jingfeng Chen, Jinnan Chen, Weikai Sun, Zhenyu Li, Lanjiong Zhao, Baozhu Zhu, Lingting Wang, Xin Liu, Qi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation Guo, Jingfeng Chen, Jinnan Chen, Weikai Sun, Zhenyu Li, Lanjiong Zhao, Baozhu Zhu, Lingting Wang, Xin Liu, Qi Computer Vision and Pattern Recognition 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. |
| title | GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.20409 |