Image Synthesis for Industrial and Environmental Scenarios

The ability to synthesize new data is essential for industrial and environmental domains. Current methods mainly focus on adversarial training for generating high-quality outputs, yet they cannot be directly applied to practical scenarios. This talk will focus on image-to-image translation tasks and show their main characteristics, limitations, and solutions proposed to overcome their drawbacks. It will also discuss recent methods for synthesizing high-quality images for industrial scenarios and new research directions to be investigated for creating optimized architectures.

About the Speaker:
Pasquale Coscia is an Assistant Professor (RTDa) at the Department of Computer Science of University of Milan (Italy) and member of the Industrial, Environmental and Biometric Informatics (IEBI) Laboratory. He received both his M.Sc. degree in Computer Engineering and Ph.D. degree in Industrial and Information Engineering from University of Campania (Italy) in 2014 and 2019, respectively. From 2019 to 2022, he was a post-doctoral researcher at University of Padova (Italy). He co-organized the Benchmarking Trajectory Forecasting Models (BTFM) workshop series at ECCV'20 and ICCV'21 and received the IVC best paper award in 2021. His main research interests are in the areas of computer vision, neural networks and machine learning.