Painterly Image Harmonization by Learning from Painterly Objects
This work addresses the problem of making composite images with photographic objects look natural in painterly backgrounds for applications in digital art and image editing, representing an incremental improvement over existing methods.
The paper tackles painterly image harmonization by learning a mapping from background style and object information to object style using painterly objects in artistic paintings, resulting in effective harmonization demonstrated on a benchmark dataset.
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 leverage 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 background style and object information to object style based on painterly objects in artistic paintings. With the learnt mapping, 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 benchmark dataset demonstrate the effectiveness of our proposed method.