ImageAdmixture: Putting Together Dissimilar Objects from Groups

Fang-Lue Zhang, Ming-Ming Cheng, Jiaya Jia, Shi-Min Hu

Abstract: We present a semiautomatic image editing framework dedicated to individual structured object replacement from groups. The major technical difficulty is element separation with irregular spatial distribution, hampering previous texture, and image synthesis methods from easily producing visually compelling results. Our method uses the object-level operations and finds grouped elements based on appearance similarity and curvilinear features. This framework enables a number of image editing applications, including natural image mixing, structure preserving appearance transfer, and texture mixing.