Saved in:
Bibliographic Details
Main Authors: Cheng, Chunyang, Xu, Tianyang, Feng, Zhenhua, Wu, Xiaojun, ZhangyongTang, Li, Hui, Zhang, Zeyang, Atito, Sara, Awais, Muhammad, Kittler, Josef
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.19854
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909531168047104
author Cheng, Chunyang
Xu, Tianyang
Feng, Zhenhua
Wu, Xiaojun
ZhangyongTang
Li, Hui
Zhang, Zeyang
Atito, Sara
Awais, Muhammad
Kittler, Josef
author_facet Cheng, Chunyang
Xu, Tianyang
Feng, Zhenhua
Wu, Xiaojun
ZhangyongTang
Li, Hui
Zhang, Zeyang
Atito, Sara
Awais, Muhammad
Kittler, Josef
contents Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms. In contrast, we propose to leverage low-level vision tasks from digital photography fusion, allowing for effective feature interaction through pixel-level supervision. This new paradigm provides strong guidance for unsupervised multimodal fusion without relying on abstract semantics, enhancing task-shared feature learning for broader applicability. Owning to the hybrid image features and enhanced universal representations, the proposed GIFNet supports diverse fusion tasks, achieving high performance across both seen and unseen scenarios with a single model. Uniquely, experimental results reveal that our framework also supports single-modality enhancement, offering superior flexibility for practical applications. Our code will be available at https://github.com/AWCXV/GIFNet.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
Cheng, Chunyang
Xu, Tianyang
Feng, Zhenhua
Wu, Xiaojun
ZhangyongTang
Li, Hui
Zhang, Zeyang
Atito, Sara
Awais, Muhammad
Kittler, Josef
Computer Vision and Pattern Recognition
Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms. In contrast, we propose to leverage low-level vision tasks from digital photography fusion, allowing for effective feature interaction through pixel-level supervision. This new paradigm provides strong guidance for unsupervised multimodal fusion without relying on abstract semantics, enhancing task-shared feature learning for broader applicability. Owning to the hybrid image features and enhanced universal representations, the proposed GIFNet supports diverse fusion tasks, achieving high performance across both seen and unseen scenarios with a single model. Uniquely, experimental results reveal that our framework also supports single-modality enhancement, offering superior flexibility for practical applications. Our code will be available at https://github.com/AWCXV/GIFNet.
title One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.19854