Artificial-intelligence-driven garment simulation: Advances, challenges, and future perspectives

Abstract

Finite-element simulation of garment represents a fundamental technology for digital design and virtual fitting; however, conventional methods are hindered by challenges such as complex modeling, difficulties in parameter acquisition, and low computational efficiency. Artificial intelligence (AI) technologies, including deep learning, physics-informed neural networks, graph neural networks, and large language models, offer novel avenues to address these limitations. This paper reviews essential AI technologies for fabric parameter identification and surrogate model construction, discusses the intelligent computer-aided engineering mechanism driven by large language models, and establishes a closed-loop intelligent simulation framework. This framework facilitates a fully automated finite-element simulation workflow, significantly reducing the modeling threshold while improving efficiency and accuracy, thus offering a new, efficient, and cost-effective paradigm for the digital transformation of the apparel industry. Finally, the paper summarizes current challenges in data management, physical consistency, and multiscale coupling, and anticipates future developments, including AI agents and digital twin garment.