Vitomir Štruc, Faculty of Electrical Engineering, University of Ljubljana
Face super-resolution: Recent advances and future challenges
Face super-resolution (or face hallucination) refers to the task of recovering high-resolution facial images from corresponding low-resolution inputs. Solutions to this task have important applications in face-oriented vision problems, such as face editing, face alignment, 3D face reconstruction, face attribute estimation and most notably face recognition. Driven by advances in deep learning, recent years have seen tremendous progress in this area with contemporary deep face hallucination models achieving formidable performance. In my presentation, I will first talk about the recent progress in the field of face super-resolution, review existing approaches and discuss the most important trends in the area. Next, I will present our solution to the problem of face hallucination, which uses explicit identity constraints in addition to the common reconstruction loss during model training and show how it compares to state-of-the-art hallucination models from the literature. I will elaborate on the main limitations of existing face super-resolution approaches and present challenges that will need to be addressed in the future. Finally, I will describe our approach to face recognition from low-resolution images that relies on super-resolution and is shown to result in state-of-the-art performance on a popular benchmark.
Vitomir Štruc is an Associate Professor at the Faculty of Electrical Engineering in Ljubljana, Slovenia. He received his PhD degree from the University of Ljubljana in 2010 and was awarded the Vodovnik award for his doctoral work in 2011. Vitomir lectures courses on the first, second and third bologna levels, including Signal Processing, Speech and Image Technologies, Biometric Systems, Language and Internet Technologies and Random Processes and Signals. Dr. Štruc was a visiting Assistant Professor at the CSE department of the University of Notre Dame, USA in 2015 and still actively collaborates with the members of the university on various projects and publications. In 2015 he received the “junior researcher award” of the University of Ljubljana for outstanding teaching and research achievements. Vitomir is an internationally recognized expert on computer vision, image processing, pattern recognition and machine learning. He authored (or co-authored) more than 100 research papers for leading international peer reviewed journals and conferences related to different areas of his research. He served in different capacities on the organizing committees of several top-tier vision conferences, including IEEE Face and Gesture, ICB, WACV and others and is currently a program co-chair for the 2020 International Joint Conference on Biometrics (IJCB). Vitomir is an Associate Editor for IEEE Transactions on Information Forensics and Security, Signal Processing, IET Biometrics and the IEEE Biometric Compendium. He also served as an Area Chair for WACV 2018, 2019, 2020, ICPR 2018, Eusipco 2019 and FG 2020. He is a member of the IEEE, IAPR, EURSIP, the national contact point for the EAB and the current president of the Slovenian Pattern Recognition Society (Slovenian branch of IAPR).