Logo of Koç Üniversitesi

Zafer Doğan - Developing tractable deep learning models for image enhancement and restoration problems

Overview

“Here we focus on image enhancement and restoration problem. Deep learning has become the method of choice for image enhancement and restoration. However, prior to the DL revolution, non-local image restoration methods, such as non-local means, and BM3D, were the dominant algorithms in the field. Here, the goal is to reconcile DL with non-local algorithms and come up with a new generation of powerful image enhancement and restoration methods. The topics include, but are not limited to:
 Image/video super-resolution
 Image/video denoising
 Image/video inpainting
 Image/video dehazing
 Image/video deblurring”