Given a composite image, image harmonization aims to adjust the foreground to make it
compatible with the background. High-resolution image harmonization is in high demand,
but still remains unexplored. Conventional image harmonization methods learn global RGB-
to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse
local context. Recent deep learning methods learn the dense pixel-to-pixel transformation
which could generate harmonious outputs, but are highly constrained in low resolution. In …