Paper
28 March 2023 Image harmonization with spatial feature interaction and back-projection upsample
Tianyanshi Liu, Yuhang Li, Youdong Ding
Author Affiliations +
Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 1256626 (2023) https://doi.org/10.1117/12.2667660
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China
Abstract
Without any processing, the synthetic image visually unrealistic due to the established differences in the appearance of the foreground and background. In view of this situation, the task of image harmonization arises at the historic moment, and its purpose is to adjust the foreground appearance of a synthesized image to be closer to the background, thereby eliminating local visual differences. However, due to the limitation of the spatial feature interaction range in the feature extraction process, the global appearance transfer effect is not good. Therefore, to solve this problem, we propose an enhanced spatial feature interaction module. Meanwhile, we propose a back-projection up sampling module, which refines the reconstruction error during the reconstruction up sampling process and better restores the details of the reconstruction foreground. Our experiments on a public dataset, iHarmony4, show that the method effectively generates synthetic images with consistent overall appearance and enhanced detail.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tianyanshi Liu, Yuhang Li, and Youdong Ding "Image harmonization with spatial feature interaction and back-projection upsample", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 1256626 (28 March 2023); https://doi.org/10.1117/12.2667660
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image enhancement

Image processing

Convolution

Education and training

Visualization

Image quality

Composites

Back to Top