High-Resolution Image Harmonization via Collaborative Dual Transformations

Wenyan Cong, Xinhao Tao, Li Niu, Jing Liang, Xuesong Gao, Qihao Sun, Liqing Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 18470-18479


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 this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end network. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution benchmark dataset and our created high-resolution real composite images demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness. Our used datasets can be found in https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Cong_2022_CVPR, author = {Cong, Wenyan and Tao, Xinhao and Niu, Li and Liang, Jing and Gao, Xuesong and Sun, Qihao and Zhang, Liqing}, title = {High-Resolution Image Harmonization via Collaborative Dual Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {18470-18479} }