Michał Szachniewicz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Michał Szachniewicz has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Maciej Zięba
Wrocław University of Science and Technology
1 shared publication - Michał Stypułkowski
Faculty of Mathematics and Computer Science, University of Wrocław, 50-384 Wrocław, Poland
1 shared publication - Wojciech Kozłowski
WUST
1 shared publication
Latest Publications
- Open Access
Dimma: Semi-Supervised Low-Light Image Enhancement with Adaptive Dimming
Enhancing low-light images with natural colors poses a challenge due to camera processing variations and limited access to ground-truth lighting conditions. To address this, we propose Dimma, a semi-supervised approach that aligns with any camera using a small set of image pairs captured under extreme lighting conditions. Our method employs a convolutional mixture density network to replicate camera-specific noise present in dark images. We enhance results further by introducing a conditional UNet architecture based on user-provided lightness values. Trained on just a few real image pairs, Dimma achieves competitive results compared to fully supervised state-of-the-art methods trained on large datasets.
Open AccessDimma: Semi-Supervised Low-Light Image Enhancement with Adaptive Dimming
Enhancing low-light images with natural colors poses a challenge due to camera processing variations and limited access to ground-truth lighting conditions. To address this, we propose Dimma, a semi-supervised approach that aligns with any camera using a small set of image pairs captured under extreme lighting conditions. Our method employs a convolutional mixture density network to replicate camera-specific noise present in dark images. We enhance results further by introducing a conditional UNet architecture based on user-provided lightness values. Trained on just a few real image pairs, Dimma achieves competitive results compared to fully supervised state-of-the-art methods trained on large datasets.