Deep Learning for 3D Fashion Design: A Survey from a Sewing Pattern-Driven Perspective

Sewing patterns form the structural foundation of the fashion industry, translating 2D conceptual designs into 3D manufacturable garments. With the rise of deep learning, 3D fashion design has seen transformative advancements, automating traditionally labor-intensive processes and enabling intelligent, data-driven workflows. Recent studies have demonstrated promising progress in areas such as sewing pattern generation, reconstruction, and 3D garment modeling. However, to date, no systematic review has specifically examined the integration of deep learning with sewing pattern-driven 3D fashion design. This survey addresses that gap by providing the first comprehensive overview of the field. We propose a novel four-stage pipeline, including representation, generation, reconstruction, and editing, to categorize and analyze current research. Within this pipeline, we review core methodologies, including geometric encoding for pattern representation, data-driven pattern generation, reconstruction from multimodal inputs (e.g., images, sketches, or text), and intuitive 3D garment editing techniques. We also consolidate existing benchmarks, covering both datasets and evaluation metrics, and contextualize the pattern-driven paradigm through comparison with alternative approaches in 2D and pattern-free 3D design. Finally, we identify key challenges, such as limited data availability and the difficulty of incorporating domain-specific design constraints, and outline future research directions to address these issues. By synthesizing current developments and structuring the research landscape, this survey serves as a foundational resource to support and accelerate innovation in manufacturable sewing pattern-driven 3D fashion design.