EUVIMEDEUVIMED entdecken
Crossref

Self-Supervision via Controlled Transformation and Unpaired Self-Conditioning for Low-Light Image Enhancement

Aupendu Kar, Sobhan Kanti Dhara, Debashis Sen, Prabir Kumar Biswas

IEEE Transactions on Instrumentation and Measurement · 2024 · 73 · 1-13

DOI: 10.1109/tim.2024.3370779 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2024. Verfasst von Aupendu Kar und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 63 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. However, it is usually challenging to create large-scale paired real-world low-light image datasets for training enhancement approaches. When trained with limited data, most supervised approaches do not perform well in generalizing to a wide variety of real-world images. In this article, we propose an unpaired low-light image enhancement network leveraging novel controlled transformation-based self-supervision and unpaired self-conditioning strategies. The model determines the required degrees of enhancement at the input image pixels, which are learned from the unpaired low-lit and well-lit images without any direct supervision. The self-supervision is based on a controlled transformation of the input image and subsequent maintenance of its enhancement in spite of the transformation. The self-conditioning performs training of the model on unpaired images such that it does not enhance an already-enhanced image or a well-lit input image. The inherent noise in the input low-light images is handled by employing low gradient magnitude suppression in a detail-preserving manner. In addition, our noise handling is self-conditioned by preventing the denoising of noise-free well-lit images. The training based on low-light image enhancement-specific attributes allows our model to avoid paired supervision without compromising significantly in performance. While our proposed self-supervision aids consistent enhancement, our novel self-conditioning facilitates adequate enhancement. Extensive experiments on multiple standard datasets demonstrate that our model, in general, outperforms the state-of-the-art both quantitatively and subjectively. Ablation studies show the effectiveness of our self-supervision and self-conditioning strategies, and the related loss functions.

Zitieren

APA

Kar, A., Dhara, S. K., Sen, D., & Biswas, P. K. (2024). Self-Supervision via Controlled Transformation and Unpaired Self-Conditioning for Low-Light Image Enhancement. IEEE Transactions on Instrumentation and Measurement, 73, 1-13. https://doi.org/10.1109/tim.2024.3370779

Vancouver

Kar A, Dhara SK, Sen D, Biswas PK. Self-Supervision via Controlled Transformation and Unpaired Self-Conditioning for Low-Light Image Enhancement. IEEE Transactions on Instrumentation and Measurement. 2024;73:1-13. doi:10.1109/tim.2024.3370779

BibTeX
@article{Kar2024,
  author = {Kar, Aupendu and Dhara, Sobhan Kanti and Sen, Debashis and Biswas, Prabir Kumar},
  title = {Self-Supervision via Controlled Transformation and Unpaired Self-Conditioning for Low-Light Image Enhancement},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2024},
  volume = {73},
  pages = {1--13},
  doi = {10.1109/tim.2024.3370779}
}
Kostenlos starten →