EUVIMEDEUVIMED entdecken
Crossref

LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction

Ao Li, Zhenyu Wang, Chen Chen, Tao Huang, Fangfang Wu, Weisheng Dong

IEEE Transactions on Image Processing · 2026 · 35 · 7700-7711

DOI: 10.1109/tip.2026.3705188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Ao Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a pseudo label-based unsupervised method called LoopExpose for arbitrary-length exposure correction. A nested loop optimization strategy is proposed to address the exposure correction problem, where the correction model and pseudo-supervised information are jointly optimized in a two-level framework. Specifically, the upper-level trains a correction model using pseudo-labels generated through multi-exposure fusion at the lower level. A feedback mechanism is introduced where corrected images are fed back into the fusion process to refine the pseudo-labels, creating a self-reinforcing learning loop. Considering the dominant role of luminance calibration in exposure correction, a Luminance Ranking Loss is introduced to leverage the relative luminance ordering across the input sequence as a self-supervised constraint. Extensive experiments on different benchmark datasets demonstrate that LoopExpose achieves superior exposure correction and fusion performance, outperforming existing state-of-the-art unsupervised methods. Code is available at https://github.com/FALALAS/LoopExpose.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, A., Wang, Z., Chen, C., Huang, T., Wu, F., & Dong, W. (2026). LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction. IEEE Transactions on Image Processing, 35, 7700-7711. https://doi.org/10.1109/tip.2026.3705188

Vancouver

Li A, Wang Z, Chen C, Huang T, Wu F, Dong W. LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction. IEEE Transactions on Image Processing. 2026;35:7700-7711. doi:10.1109/tip.2026.3705188

BibTeX
@article{Li2026,
  author = {Li, Ao and Wang, Zhenyu and Chen, Chen and Huang, Tao and Wu, Fangfang and Dong, Weisheng},
  title = {LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {7700--7711},
  doi = {10.1109/tip.2026.3705188}
}
Kostenlos starten →