Painterly Image Harmonization via Adversarial Residual Learning
This addresses the challenge of creating natural-looking composite images in photo editing, particularly for artistic backgrounds, but it is incremental as it builds on existing adversarial learning approaches.
The paper tackled the problem of painterly image harmonization, where a photorealistic foreground object is inserted into an artistic background, by using adversarial learning to bridge the domain gap, resulting in more harmonious and visually appealing outcomes compared to previous methods.
Image compositing plays a vital role in photo editing. After inserting a foreground object into another background image, the composite image may look unnatural and inharmonious. When the foreground is photorealistic and the background is an artistic painting, painterly image harmonization aims to transfer the style of background painting to the foreground object, which is a challenging task due to the large domain gap between foreground and background. In this work, we employ adversarial learning to bridge the domain gap between foreground feature map and background feature map. Specifically, we design a dual-encoder generator, in which the residual encoder produces the residual features added to the foreground feature map from main encoder. Then, a pixel-wise discriminator plays against the generator, encouraging the refined foreground feature map to be indistinguishable from background feature map. Extensive experiments demonstrate that our method could achieve more harmonious and visually appealing results than previous methods.