5 papers
BuildMamba: A Visual State-Space Based Model for Multi-Task Building Segmentation and Height Estimation from Satellite Images
Sinan U. Ulu, A. Enes Doruk, I. Can Yagmur +3
Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability…
XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration
Ismail Can Yagmur, Hasan F. Ates, Bahadir K. Gunturk
Accurate multispectral image matching presents significant challenges due to non-linear intensity variations across spectral modalities, extreme viewpoint changes, and the scarcity…
HSTR-Net: Reference Based Video Super-resolution with Dual Cameras
H. Umut Suluhan, Abdullah Enes Doruk, Hasan F. Ates +1
High-spatio-temporal resolution (HSTR) video recording plays a crucial role in enhancing various imagery tasks that require fine-detailed information. State-of-the-art cameras prov…
Learning Binary Color Filter Arrays with Trainable Hard Thresholding
Cemre Omer Ayna, Bahadir Kursat Gunturk, Ali Cafer Gurbuz
Color Filter Arrays (CFA) are optical filters in digital cameras that capture specific color channels. Current commercial CFAs are hand-crafted patterns with different physical and…
Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimation
Hasan F. Ates, Suleyman Yildirim, Bahadir K. Gunturk
Blind single image super-resolution (SISR) is a challenging task in image processing due to the ill-posed nature of the inverse problem. Complex degradations present in real life i…