EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Exposure HDR Imaging: A Review of Pixel-Level and Feature-Level Reconstruction Methods

Qian Tao iD, Wei Wang iD, Chaobing Zheng iD, Zhengguo Li iD

Sensors · 22.07.2026 · 26 (14) · 4649

DOI: 10.3390/s26144649 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.07.2026. Verfasst von Qian Tao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, School of Computer Science and Technology, Wuhan…. Die Arbeit nennt 151 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-exposure is an efficient way to capture real-world high-dynamic-range (HDR) scenes. However, HDR imaging suffers from severe ghosting artifacts in dynamic scenes due to the temporal gap between sequential exposures. In this article, we categorize the literature on two important topics on HDR imaging: multi-exposure fusion (MEF) and ghost removal. Conventional filter-based and data-driven methods are studied in pixel space and feature space. For popular deep learning-based approaches, we provide a granular taxonomy based on their alignment and fusion domains: pixel-space methods, which typically employ explicit motion compensation such as optical flow or spatial transformers, and feature-space methods, which leverage implicit alignment through deformable convolutions, attention mechanisms, or latent representation merging. Representative works are compared across different supervision settings, and key design principles are summarized. In addition, this survey summarizes commonly used datasets and evaluation metrics, discussing their applicability under diverse output forms. Finally, major bottlenecks and promising directions for future research are outlined.

Schlagwörter

Stichwörter der Autor:innen

deep learningfeature spacefilter-basedghost removalhigh-dynamic-range imagingmulti-exposure fusionpixel space

Autor:innen und Institutionen

  • Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430081, China.
  • School of Electronic Information, Wuhan University of Science and Technology, Wuhan 430081, China.
  • Institute of Advanced Intelligence and Computing, A*STAR, Singapore 138632, Singapore.

ORCID-Profile: Qian Tao, Wei Wang, Chaobing Zheng, Zhengguo Li

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Tao, Q., Wang, W., Zheng, C., & Li, Z. (2026). Multi-Exposure HDR Imaging: A Review of Pixel-Level and Feature-Level Reconstruction Methods. Sensors, 26(14), 4649. https://doi.org/10.3390/s26144649

Vancouver

Tao Q, Wang W, Zheng C, Li Z. Multi-Exposure HDR Imaging: A Review of Pixel-Level and Feature-Level Reconstruction Methods. Sensors. 2026;26(14):4649. doi:10.3390/s26144649

BibTeX
@article{Tao2026,
  author = {Tao, Qian and Wang, Wei and Zheng, Chaobing and Li, Zhengguo},
  title = {Multi-Exposure HDR Imaging: A Review of Pixel-Level and Feature-Level Reconstruction Methods},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4649},
  doi = {10.3390/s26144649}
}
Kostenlos starten →