High-resolution image harmonization via collaborative dual transformations

W Cong, X Tao, L Niu, J Liang, X Gao… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …

[引用][C] High-resolution image harmonization via collaborative dual transformations. In 2022 IEEE

W Cong, X Tao, L Niu, J Liang, X Gao, Q Sun, L Zhang - CVF Conference on …, 2022
以上显示的是最相近的搜索结果。 查看全部搜索结果