EUVIMEDEUVIMED entdecken
Crossref

Unsupervised Illumination Adaptation for Low-Light Vision

Wenjing Wang, Rundong Luo, Wenhan Yang, Jiaying Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-09 · 46 (9) · 5951-5966

DOI: 10.1109/tpami.2024.3382108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-09. Verfasst von Wenjing Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 99 Literaturangaben. Gefördert von: National Natural Science Foundation of China, AI Joint Lab of Future Urban Infrastructure, Boyun Vision Company Ltd.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Insufficient lighting poses challenges to both human and machine visual analytics. While existing low-light enhancement methods prioritize human visual perception, they often neglect machine vision and high-level semantics. In this paper, we make pioneering efforts to build an illumination enhancement model for high-level vision. Drawing inspiration from camera response functions, our model could enhance images from the machine vision perspective despite being lightweight in architecture and simple in formulation. We also introduce two approaches that leverage knowledge from base enhancement curves and self-supervised pretext tasks to train for different downstream normal-to-low-light adaptation scenarios. Our proposed framework overcomes the limitations of existing algorithms without requiring access to labeled data in low-light conditions. It facilitates more effective illumination restoration and feature alignment, significantly improving the performance of downstream tasks in a plug-and-play manner. This research advances the field of low-light machine analytics and broadly applies to various high-level vision tasks, including classification, face detection, optical flow estimation, and video action recognition.

Förderung

  • National Natural Science Foundation of China
  • AI Joint Lab of Future Urban Infrastructure
  • Boyun Vision Company Ltd

Zitieren

APA

Wang, W., Luo, R., Yang, W., & Liu, J. (2024). Unsupervised Illumination Adaptation for Low-Light Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(9), 5951-5966. https://doi.org/10.1109/tpami.2024.3382108

Vancouver

Wang W, Luo R, Yang W, Liu J. Unsupervised Illumination Adaptation for Low-Light Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(9):5951-5966. doi:10.1109/tpami.2024.3382108

BibTeX
@article{Wang2024,
  author = {Wang, Wenjing and Luo, Rundong and Yang, Wenhan and Liu, Jiaying},
  title = {Unsupervised Illumination Adaptation for Low-Light Vision},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {9},
  pages = {5951--5966},
  doi = {10.1109/tpami.2024.3382108}
}
Kostenlos starten →