Pacific Graphics 2013 B. Levy, X. Tong, and K. Yin (Guest Editors) Volume 32 (2013), Number 7 Stroke-guided Image Synthesis for Skeletal Structure Editing Sheng-Jie Luo 1 Chin-Yu Lin 1 I-Chao Shen 2 Bing-Yu Chen 1 1 National Taiwan University 2 Academia Sinica (a) Input image object stroke control point (b) Several variations of the input image object with skeletal structure manipulations S2 S1 S1 S1 S1 S1 S1 S1 S1 S1 S2 S2 Figure 1: Technique for synthesizing image objects with various skeletal structures (b) with reference to an input image object (a). A user firstly annotates two strokes S1 and S2 to indicate the skeletal structures on the input object that is used to synthesize the new objects, and then draws several strokes that correspond to S1 and S2 in the output domain. Finally, the method synthesizes the objects with respect to these strokes. Abstract Creating variations of an image object is an important task, which usually requires manipulating the skeletal structure of the object. However, most existing methods (such as image deformation) only allow for stretching the skeletal structure of an object: modifying skeletal topology remains a challenge. This paper presents a technique for synthesizing image objects with different skeletal structures while respecting to an input image object. To apply this technique, a user firstly annotates the skeletal structure of the input object by specifying a number of strokes in the input image, and draws corresponding strokes in an output domain to generate new skeletal structures. Then, a number of the example texture pieces are sampled along the strokes in the input image and pasted along the strokes in the output domain with their orientations. The result is obtained by optimizing the texture sampling and seam computation. The proposed method is successfully used to synthesize challenging skeletal structures, such as skeletal branches, and a wide range of image objects with various skeletal structures, to demonstrate its effectiveness. Categories and Subject Descriptors (according to ACM CCS): I.3.3 [Computer Graphics]: Picture/Image Generation—; I.4.9 [Image Processing and Computer Vision]: Applications— 1. Introduction Creating variations of an image object is an important task for many computer graphics and image processing ap- plications, which usually involves manipulating the skele- tal structure of the object. Existing structural image ma- nipulation techniques are based on either image warping approaches [IMH05, WTSL08, LGJA09, CAA09, CAA10] which stretch the image to satisfy the editing constraints, or texture synthesis approaches [KEBK05], which synthe- size repeated textures to fill the target image domain, so that the result resembles the input image. However, both classes c  2013 The Author(s) Computer Graphics Forum c  2013 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.