no code implementations • 26 Mar 2021 • Aamir Mustafa, Aliaksei Mikhailiuk, Dan Andrei Iliescu, Varun Babbar, Rafal K. Mantiuk
The choice of a loss function is an important factor when training neural networks for image restoration problems, such as single image super resolution.
no code implementations • 19 Dec 2020 • Aliaksei Mikhailiuk, Maria Perez-Ortiz, Dingcheng Yue, Wilson Suen, Rafal K. Mantiuk
As the existing HDR quality datasets are limited in size, we created a Unified Photometric Image Quality dataset (UPIQ) with over 4, 000 images by realigning and merging existing HDR and standard-dynamic-range (SDR) datasets.
1 code implementation • 12 Apr 2020 • Aliaksei Mikhailiuk, Clifford Wilmot, Maria Perez-Ortiz, Dingcheng Yue, Rafal Mantiuk
In this paper we propose ASAP, an active sampling algorithm based on approximate message passing and expected information gain maximization.