Towards automatic digital garment assembly
Computer Science > Computer Vision and Pattern Recognition arXiv:2610.20651 (cs) [Submitted on 12 Oct 2026] Title: Towards automatic digital garment assembly Authors: Alejandro Rodriguez.
计算机科学 > 计算机视觉与模式识别 arXiv:2610.20651 (cs) [提交于 2026 年 10 月 12 日] 标题：迈向自动数字服装装配 作者：Alejandro Rodriguez。
Abstract: Creating digital garments from existing two-dimensional patterns remains a time-consuming process. Although patterns are widely available in digital form, their assembly in garment CAD software involves manual definition of sewing operations and arrangement of the pattern panels for drape simulation.
摘要：利用现有的二维纸样创建数字服装仍然是一个耗时的过程。尽管纸样在数字形式上已广泛可用，但在服装 CAD 软件中进行装配时，仍需手动定义缝纫操作并排列纸样裁片以进行悬垂模拟。
We present two learning-based approaches that automate both tasks using the 2D vector pattern as their sole input. Our automatic sewing model operates at the segment level, leveraging a Transformer encoder with multiple prediction heads.
我们提出了两种基于学习的方法，仅使用二维矢量纸样作为输入即可自动完成这两项任务。我们的自动缝纫模型在片段级别运行，利用带有多个预测头的 Transformer 编码器。
Our novel architecture supports many-to-many, ordered segment correspondences, as well as hems, overlapping seams needed for multilayer garments, and construction properties such as seam allowances and stitch types, required for the finished virtual garment but neglected by previous methods.
我们新颖的架构支持多对多、有序的片段对应关系，以及卷边、多层服装所需的重叠接缝，以及缝份和针迹类型等结构属性；这些属性对于成品虚拟服装至关重要，但以往的方法却忽略了它们。
A complementary panel-level model predicts body-region assignments, layers, and placement coordinates to initialize the drape simulation. We evaluate both models on a curated dataset of 4,035 professionally assembled garment instances.
一个互补的裁片级模型负责预测身体区域分配、层级和放置坐标，以初始化悬垂模拟。我们在一个包含 4,035 个专业装配服装实例的精选数据集上评估了这两个模型。
The sewing model exactly recovers all seam and hem topologies of 63.3% of test garments, while the arrangement model meets the specified placement criteria for all panels in 66.2% of test garments. We also integrate both methods into garment CAD software, demonstrating automatic assembly of successfully predicted garments.
缝纫模型准确恢复了 63.3% 测试服装的所有接缝和卷边拓扑结构，而排列模型在 66.2% 的测试服装中满足了所有裁片的指定放置标准。我们还将这两种方法集成到服装 CAD 软件中，演示了成功预测服装的自动装配过程。