During this winter, I spent almost three months at the Multimedia Signal Processing Workgroup led by Prof. Dietmar Saupe at the University of Konstanz. During this stay I had the opportunity to meet many researchers who work in image and video quality assessment and pursue my research work.
I focused on predicting the satisfied user ratio of compressed images during the visiting program. The human’s visual satisfaction may be degraded by image compression. We proposed a deep learning approach (SUR-net) for predicting the satisfied user ratio curve of compressed images. These days we are still working for the manuscript. Hopefully, we will publish this work in Qomex 2019.
Konstanz is a beautiful city full of natural scenes. I was very happy during the stay there. I really enjoyed the experience of working with researchers at the Multimedia Signal Processing Workgroup. I thank the SFB-TRR 161 for the support and the funding
