EUVIMEDEUVIMED entdecken
Crossref

Rethinking Multi-Focus Image Fusion: An Input Space Optimization View

Zeyu Wang, Shuang Yu, Haoran Duan, Shidong Wang, Yang Long, Ling Shao

IEEE Transactions on Image Processing · 2026 · 35 · 1321-1336

DOI: 10.1109/tip.2026.3654370 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Zeyu Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Liaoning Province, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-focus image fusion (MFIF) addresses the challenge of partial focus by integrating multiple source images taken at different focal depths. Unlike most existing methods that rely on complex loss functions or large-scale synthetic datasets, this study approaches MFIF from a novel perspective: optimizing the input space. The core idea is to construct a high-quality MFIF input space in a cost-effective manner by using intermediate features from well-trained, non-MFIF networks. To this end, we propose a cascaded framework comprising two feature extractors, a Feature Distillation and Fusion Module (FDFM), and a focus segmentation network Y ${}^{U}$ Net. Based on our observation that discrepancy and edge features are essential for MFIF, we select a image deblurring network and a salient object detection network as feature extractors. To transform these extracted features into an MFIF-suitable input space, we propose FDFM as a training-free feature adapter. To make FDFM compatible with high-dimensional feature maps, we extend the manifold theory from the edge-preserving field and design a novel isometric domain transformation. Extensive experiments on six benchmark datasets show that 1) our model consistently outperforms 13 state-of-the-art methods in both qualitative and quantitative evaluations, and 2) the constructed input space can directly enhance the performance of many MFIF models without additional requirements.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Liaoning Province
  • Fundamental Research Funds for the Central Universities
  • Natural Science Foundation of Heilongjiang Province

Zitieren

APA

Wang, Z., Yu, S., Duan, H., Wang, S., Long, Y., & Shao, L. (2026). Rethinking Multi-Focus Image Fusion: An Input Space Optimization View. IEEE Transactions on Image Processing, 35, 1321-1336. https://doi.org/10.1109/tip.2026.3654370

Vancouver

Wang Z, Yu S, Duan H, Wang S, Long Y, Shao L. Rethinking Multi-Focus Image Fusion: An Input Space Optimization View. IEEE Transactions on Image Processing. 2026;35:1321-1336. doi:10.1109/tip.2026.3654370

BibTeX
@article{Wang2026,
  author = {Wang, Zeyu and Yu, Shuang and Duan, Haoran and Wang, Shidong and Long, Yang and Shao, Ling},
  title = {Rethinking Multi-Focus Image Fusion: An Input Space Optimization View},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {1321--1336},
  doi = {10.1109/tip.2026.3654370}
}
Kostenlos starten →