Title: A New Optimization Objective for Inverse Problems

Presented By: Raja Giryes, Tel-Aviv University

Abstract:

Most techniques for solving inverse problems in image processing aims at minimizing an optimization objective that is composed of a fidelity term and a prior. While most approaches focus on improving the prior term, in our work, we propose a novel fidelity term. We show how this new objective leads to a strategy for solving inverse problems just by using a denoiser or a trained generative adversarial network (GAN). We present the advantage of our solution both theoretically and empirically in solving various problems such as image deblurring, super-resolution, and compressed sensing.

Biography:

Raja Giryes is an assistant professor in the school of electrical engineering at Tel Aviv University. He received the B.Sc (2007), M.Sc. (supervision by Prof. M. Elad and Prof. Y. C. Eldar, 2009), and PhD (supervision by Prof. M. Elad 2014) degrees from the Department of Computer Science, The Technion - Israel Institute of Technology, Haifa. Raja was a postdoc at the computer science department at the Technion (Nov. 2013 till July 2014) and at the lab of Prof. G. Sapiro at Duke University, Durham, USA (July 2014 and Aug. 2015). His research interests lie at the intersection between signal and image processing and machine learning, and in particular, in deep learning, inverse problems, sparse representations, and signal and image modeling. Raja received the EURASIP best PhD award, the ERC-StG grant, Maof prize for excellent young faculty (2016-2019), VATAT scholarship for excellent postdoctoral fellows (2014-2015), Intel Research and Excellence Award (2005, 2013), the Excellence in Signal Processing Award (ESPA) from Texas Instruments (2008) and was part of the Azrieli Fellows program (2010-2013).

**Lunch will be provided**

To meet with Raja, please email harel.haim.hh@gmail.com