Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles
Abstract
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.
Cite
Text
Niu et al. "Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I5.28232Markdown
[Niu et al. "Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/niu2024aaai-progressive/) doi:10.1609/AAAI.V38I5.28232BibTeX
@inproceedings{niu2024aaai-progressive,
title = {{Progressive Painterly Image Harmonization from Low-Level Styles to High-Level Styles}},
author = {Niu, Li and Hong, Yan and Cao, Junyan and Zhang, Liqing},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {4352-4360},
doi = {10.1609/AAAI.V38I5.28232},
url = {https://mlanthology.org/aaai/2024/niu2024aaai-progressive/}
}