Design preserving garment transfer

Abstract

We present a fully automatic method for design-preserving transfer of garments between characters with different body shapes. For real-life garments, such transfer is performed through a knowledge intensive and time consuming process, known as pattern grading . Our first contribution is to reformulate the criteria used in professional pattern-grading as a set of geometric requirements, respectively expressing shape or design preservation, proportionality, and fit. We then propose a fully automatic garment transfer algorithm which satisfies all of these criteria while ensuring the physical plausibility of the result. Specifically, we formulate garment transfer as a constrained optimization problem and solve it efficiently through iterative quadratic minimization. As demonstrated by our results, our method is able to automatically generate design-preserving versions of existing garments for target characters whose proportions and body shape significantly differ from those of the source. The method correctly handles the transfer of multiple layers of garment. Lastly, when source 2D patterns are available, we output graded patterns suitable for manufacturing the transferred garments. Our fully automatic design-preserving transfer method leads to significant time savings for both computer artists and fashion designers.