ACM MM 19 TPC Meeting Workshop

In this talk I discussed recent advancements we made in removing compression artifacts using Generative Adversarial Networks. I presented recent results published in our IEEE TMM paper: “Deep Universal Generative Adversarial Compression Artifact Removal”, 2019. This will cover how to deal with compression artifacts using GANs without knowing coding parameters in advance, some caveats on the evaluation of results and some recent unpublished evaluation protocols we devised exploiting semantic tasks instead of signal based metrics. Finally, from a system point of view, I discussed how the generator architecture can be modified to attain real-time performance.

Lorenzo Seidenari
Lorenzo Seidenari
Assistant Professor of Computer Engineering

I am an Assistant Professor (Tenure Track) of Computer Engineering at the University of Florence working on Deep Learning and Computer Vision.