Parallel Style-aware Image Cloning for Artworks


IEEE Transactions on Visualization and Computer Graphics, IEEE Computer Society, 2015, 21(2): 229-240.

Yandan Zhao, Xiaogang Jin, Yingqing Xu, Hanli Zhao, Meng Ai, Kun Zhou


(a) Inputs;                                                                                                                         (b) our result.
Given some objects (a girl and a wolf) and a pastel landscape drawing, our method creates a scene of Little Red Riding Hood by seamlessly integrating the objects into the given artwork. 


We present style-aware image cloning, a novel image editing approach for artworks, which allows users to seamlessly insert any photorealistic or artificial objects into an artwork to create a new image that shares the same artistic style with the original artwork. To this end, a real-time image transfer algorithm is developed to stylize the cloned object according to a distance metric based on the artistic styles and semantic information. Several interactive functions, such as layering, shadowing, semantic labeling, and direction field editing, are provided to enhance the harmonization of the composite image. Extensive experimental results demonstrate the effectiveness of our method.