Deep Image Harmonization by Bridging the Reality Gap
Junyan Cao (Shanghai Jiao Tong University), Wenyan Cong (Shanghai Jiao Tong University), Li Niu (Shanghai Jiao Tong University),* Jianfu Zhang (Shanghai Jiao Tong University), Liqing Zhang (Shanghai Jiao Tong University)
The 33rd British Machine Vision Conference
Abstract
Image harmonization has been significantly advanced with large-scale harmonization dataset. However, the current way to build dataset is still labor-intensive, which adversely affects the extendability of dataset. To address this problem, we propose to construct rendered harmonization dataset with fewer human efforts to augment the existing real-world dataset. To leverage both real-world images and rendered images, we propose a cross-domain harmonization network to bridge the domain gap between two domains. Moreover, we also employ well-designed style classifiers and losses to facilitate cross-domain knowledge transfer. Extensive experiments demonstrate the potential of using rendered images for image harmonization and the effectiveness of our proposed network.Video
Citation
@inproceedings{Cao_2022_BMVC,
author = {Junyan Cao and Wenyan Cong and Li Niu and Jianfu Zhang and Liqing Zhang},
title = {Deep Image Harmonization by Bridging the Reality Gap},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0023.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by