EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Low-Light Monocular Depth Estimation Algorithm Based on Illumination Adaptive Image Enhancement

Xiaoqian Cao iD, Yang Wang, Wanyu Li iD, Weifeng Liu iD

Sensors · 10.05.2026 · 26 (10) · 3002

DOI: 10.3390/s26103002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.05.2026. Verfasst von Xiaoqian Cao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Control Engineering, Shaanxi University of Science and Technology, Xi'an 710021, China. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, natural science foundation of shaanxi province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depth estimation in low-light scenes is an enormous challenge in the field of monocular depth estimation. Although numerous algorithms have attempted to improve their performance in low-light scenarios through a variety of techniques, the inconsistent illumination issue caused by local intense or colored light is rarely taken into consideration. To tackle this problem, we proposed an illumination adaptive image enhancement-based low-light depth estimation algorithm (IAIE_LDE) in this paper. Our main contribution is an S-shaped illumination estimation basis illumination adaptive consistent correction model, which is designed to eliminate the edge blurring and depth hole effects in depth maps caused by inconsistent lighting. Meanwhile, a low-light depth estimation architecture consisting of three modules, namely, illumination adaptive correction, low-light image enhancement and depth estimation modules, is constructed and trained. Specifically, the first sub-module is designed to alleviate the illumination inconsistency utilizing the proposed S-shaped illumination adaptive correction model by calculating the corresponding correction coefficients for each pixel according to the estimated illumination; the core module of the classic EnlightGAN algorithm is adopted in the second sub-module to improve the overall brightness of the image and solve the other problems caused by low light; the ZoeDepth model is chosen as our depth estimation sub-module to output a depth map comparable to high-quality illuminated images. Extensive experiments on the widely used Oxford RobotCar and nuScenes datasets indicate superior performance of our method by comparing it with state-of-the-art low-light depth estimation algorithms such as RNW, STEPS, ADDS-DepthNet, and ACDepth, both qualitatively and quantitatively.

Schlagwörter

Stichwörter der Autor:innen

depth estimationillumination inconsistent correctionimage enhancementlow-light scene

Autor:innen und Institutionen

  • School of Electronic and Control Engineering, Shaanxi University of Science and Technology, Xi'an 710021, China.
  • School of Electromechanical and Automation, Huaqiao University, Xiamen 361021, China.

ORCID-Profile: Xiaoqian Cao, Wanyu Li, Weifeng Liu

Förderung

  • National Natural Science Foundation of China
  • natural science foundation of shaanxi province

Zitieren

APA

Cao, X., Wang, Y., Li, W., & Liu, W. (2026). Low-Light Monocular Depth Estimation Algorithm Based on Illumination Adaptive Image Enhancement. Sensors, 26(10), 3002. https://doi.org/10.3390/s26103002

Vancouver

Cao X, Wang Y, Li W, Liu W. Low-Light Monocular Depth Estimation Algorithm Based on Illumination Adaptive Image Enhancement. Sensors. 2026;26(10):3002. doi:10.3390/s26103002

BibTeX
@article{Cao2026,
  author = {Cao, Xiaoqian and Wang, Yang and Li, Wanyu and Liu, Weifeng},
  title = {Low-Light Monocular Depth Estimation Algorithm Based on Illumination Adaptive Image Enhancement},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3002},
  doi = {10.3390/s26103002}
}
Kostenlos starten →