Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles
This addresses the problem of harmonizing photographic objects on painterly backgrounds for image editing applications, representing an incremental improvement over existing methods.
The paper tackles painterly image harmonization by developing a progressive multi-stage network that harmonizes composite foregrounds from low-level to high-level styles, achieving better interpretability and performance than previous auto-encoder based methods, with an early-exit strategy to skip unnecessary late stages.
Painterly image harmonization aims to harmonize a photographic foreground object on the painterly background. Different from previous auto-encoder based harmonization networks, we develop a progressive multi-stage harmonization network, which harmonizes the composite foreground from low-level styles (e.g., color, simple texture) to high-level styles (e.g., complex texture). Our network has better interpretability and harmonization performance. Moreover, we design an early-exit strategy to automatically decide the proper stage to exit, which can skip the unnecessary and even harmful late stages. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our progressive harmonization network.