Application-Guided Image Fusion: A Path to Improve Results in High-Level Vision Tasks

Gisel Bastidas-Guacho, Gisel Bastidas-Guacho, Patricio Moreno-Vallejo, Patricio Moreno-Vallejo, Boris Vintimilla, Angel Sappa, Angel Sappa

2025

Abstract

This paper proposes an enhanced application-driven image fusion framework to improve final application results. This framework is based on a deep learning architecture that generates fused images to better align with the requirements of applications such as semantic segmentation and object detection. The color-based and edge-weighted correlation loss functions are introduced to ensure consistency in the YCbCr space and emphasize structural integrity in high-gradient regions, respectively. Together, these loss components allow the fused image to retain more features from the source images by producing an application-ready fused image. Experiments conducted on two public datasets demonstrate a significant improvement in mIoU achieved by the proposed approach compared to state-of-the-art methods.

Paper Citation

in Harvard Style

Bastidas-Guacho G., Moreno-Vallejo P., Vintimilla B. and Sappa A. (2025). Application-Guided Image Fusion: A Path to Improve Results in High-Level Vision Tasks. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 178-187. DOI: 10.5220/0013307300003912

in Bibtex Style

@conference{visapp25,
author={Gisel Bastidas-Guacho and Patricio Moreno-Vallejo and Boris Vintimilla and Angel Sappa},
title={Application-Guided Image Fusion: A Path to Improve Results in High-Level Vision Tasks},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={178-187},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013307300003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Application-Guided Image Fusion: A Path to Improve Results in High-Level Vision Tasks
SN - 978-989-758-728-3
AU - Bastidas-Guacho G.
AU - Moreno-Vallejo P.
AU - Vintimilla B.
AU - Sappa A.
PY - 2025
SP - 178
EP - 187
DO - 10.5220/0013307300003912
PB - SciTePress