TY - JOUR
AU - Lyu, Yingrui
AB - 3D garment models enhance the consumer experience by enabling virtual trying-on and personalized customization. Additionally, they streamline design and manufacturing processes, reduce resource waste, and drive the garment industry toward greater digitalization and sustainability. Nevertheless, the complexities of 3D garment modeling have impeded its widespread adoption. Recent significant advances in deep learning have catalyzed improvements in 3D garment model generation. This technology circumvents traditional time-consuming 3D modeling processes, enabling the direct generation of 3D garment models, and has garnered substantial attention. This paper presents a comprehensive and systematic review of advances in deep learning for 3D garment generation. It commences with an introduction to essential preliminaries, encompassing data representations, generation objectives and tasks, generative models, datasets, and evaluation methods. The review categorizes works in 3D garment generation into three distinct areas: mesh, texture, and pattern generation, providing an in-depth analysis of the most recent and advanced methods. Furthermore, the paper examines applications of 3D garment generation, discusses current challenges, and proposes directions for future research, offering valuable insights for continued exploration in this rapidly expanding field.
TI - Deep learning for 3D garment generation: A review
JF - Textile Research Journal
DO - 10.1177/00405175251335188
DA - 2025-01-01
UR - https://www.deepdyve.com/lp/sage/deep-learning-for-3d-garment-generation-a-review-UgUWVeh4Bt
VL - OnlineFirst
IS - 
DP - DeepDyve
ER -