Md Raihan Khan

Md Raihan Khan

Lecturer in EEE at North Western University, Bangladesh. Research in deep learning for biomedical signal processing and medical imaging.

Custom Dataset-driven Unsupervised Low-light Image Enhancement using 2D CNN

Published in IEEE International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), 2025, 2025

This paper proposes an unsupervised 2D CNN framework for low-light image enhancement, trained on a custom dataset of real-world low-light images. Without paired ground truth, the method relies on self-supervised constraints and image statistics to improve brightness and contrast while preserving structural details.

Experimental results show significant qualitative and quantitative improvements over classical enhancement techniques, validating the effectiveness of the unsupervised CNN design.

Recommended citation: Airin Akter Tania, Md Raihan Khan, and Mohiuddin Ahmad, "Custom Dataset-driven Unsupervised Low-light Image Enhancement using 2D CNN," IEEE QPAIN 2025.
Download Paper