Paper
21 June 2024 Reference-based attention mechanism and region segmentation line art colorization
Wenqiang Ye, Feifan Cai, Youdong Ding
Author Affiliations +
Proceedings Volume 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024); 131671K (2024) https://doi.org/10.1117/12.3029682
Event: International Conference on Remote Sensing, Mapping and Image Processing (RSMIP 2024), 2024, Xiamen, China
Abstract
Automatic line art colorization has been largely adapted to the anime industry since it can improve animation production. Reference-based method provides a more convenient and intuitive method but now is equipped with a challenge in aspects of color match and semantic consistency. In this paper, we propose an GAN-based line art colorization architecture. We introduce an attention mechanism module which fuses and merges coordinate attention and stop-gradient attention for improving encoder's ability of key region perception and feature extraction. To alleviate color overflow, we design a segmentation branch to control the region correspondence between the line art and the reference image. Multiple experiments unequivocally illustrate that our method excels over other state-of-the-art reference-based techniques in animation line art colorization task.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Wenqiang Ye, Feifan Cai, and Youdong Ding "Reference-based attention mechanism and region segmentation line art colorization", Proc. SPIE 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024), 131671K (21 June 2024); https://doi.org/10.1117/12.3029682
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Color

Image segmentation

Feature extraction

Semantics

Color image processing

Back to Top