Painterly Image Harmonization by Learning from Painterly Objects

Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the background. Despite the competitive performance of existing painterly harmonization works, they did not fully lever-age the painterly objects in artistic paintings. In this work, we explore learning from painterly objects for painterly image harmonization. In particular, we learn a mapping from back-ground style and object information to object style based on painterly objects in artistic paintings. With the learnt map-ping, we can hallucinate the target style of composite object, which is used to harmonize encoder feature maps to produce the harmonized image. Extensive experiments on the bench-mark dataset demonstrate the effectiveness of our proposed method.