Image‐based embroidery modeling and rendering

Abstract

Embroidery is a traditional handicraft of sewing stitches into fabric or other materials in different patterns, and this ancient non‐photorealistic art form has not drawn enough attention thus far. In this paper, we present an image‐based method to simulate the traditional embroidery art. The method combines stroke‐based rendering techniques with the Phong lighting model to create picturesque embroidery‐like images. We first build a 3D stitch model and derive some most commonly used stitch patterns from it. Then we preprocess the input image by segmenting it into regions, from which the parameters to specify stitch patterns are obtained. Finally, we apply stitches back onto the desired regions and render them under a virtual light source. Experimental results show that our method, different from the existing schemes, is capable of performing fine embroidery simulations with the effects of lighting and shading based on an input image. Copyright © 2016 John Wiley & Sons, Ltd.

Automatic embroidery texture synthesis for garment design and online display

“…Chen et al presented a linedrawing-based method [7] which uses clean embroidery patterns as input, and relies on user interaction to decide the stitch style. Cui et al [9] also left the segmentation of complicated reference images and the selection of stitch style as the future work. The level of human intervention in these aforementioned methods restricts their applications which require fast response.…”

“…In the stitch-style-based texture synthesis, we fill each region with an embroidery pattern independently with three types of stitches (the long-short stitch, the satin stitch and the edge stitch) similar to Cui et al [9]. Our system stores three types of preset reference textures, which will be recolored for each different region before synthesis.…”

“…The long-short stitch (see Fig. 4(a)) is a traditional stitch, which consists of rows of stitches to show intensity graduation [7,9]. The number of repetition in each stitch row can vary with the width, making the longshort stitch flexible to fit any shapes, especially for the large areas or shapes with irregular contours.…”

“…Owing to its labor-intensive manual work and training, it is prohibitively slow to visualize an embroidery design without completing at least some of the actual work physically. Existing procedures deal with this problem via deep neural networks [23], patch-based methods [22], or image-based interactive methods [7,9], which greatly rely on reference images or require complex user interaction. We argue that this problem can be solved by automated style-transfer from design images to their embroidery-style correspondences using texture synthesis, and thus design an automated tool for embroidery design visualization.…”

“…1(c) and (d)). Some methods [7,9] rely heavily on user interaction to perform the segmentation and stitch style selection, which is very time-consuming when the content of the image is complex; while others impose restrictions on the input images, making them impractical when dealing with various types of user input. Specifically, existing methods [21,24,23] are simply designed for a particular embroidery stitch style, and cannot be easily generalized for other widely-used stitches such as the satin stitch used in folk handicraft and the cos-…”