Modeling Garment Seam from a Single Image

We propose an automatic garment seam modeling framework to create a garment model with the seam structure from a single image. In order to achieve this, a marked seam image database and parametric seam models have been set up. Given a real seam image, we first identify the type of the seam image based on our marked seam image database and seam parameters are parsed automatically by our sewing thread estimation method. Then the seam initial model is generated through the pre-defined seam parametric models. A garment model with the seam structure is finally obtained based on the seam position information which users have marked on the garment. Moreover, we verify the effectiveness of our method with numerous experiments.