【学术报告】Neural Style Transfer with Additional Information

【主讲人】 Prof. Paul Rosin  (Cardiff University, UK)

【时  间】 2019年9月16日（周一）上午10:00—12:00

【地  点】 北京大学王选所大楼106会议室

Abstract:

I will start with an overview of some of my earlier non-photorealistic rendering (NPR) work, and then briefly cover my more recent work on neural style transfer.  Specifically, the latter methods incorporate additional information: Depth-aware Neural Style Transfer, Neural Style Transfer with Semantic Masks and Neural Style Transfer with Local Models. If time permits I will also talk about some examples and approaches to evaluating computer vision algorithms.

Biography:

Prof. Paul Rosin received the Ph.D. degree in Information Engineering from City University, London in 1988. At the beginning of 2000 he moved to the School of Computer Science & Informatics, Cardiff University. He is currently a Professor of Computer Vision at School of Computer Science & Informatics, Cardiff University, UK.

His research interests include the representation, segmentation, and grouping of curves, knowledge-based vision systems, early image representations, low level image processing, machine vision approaches to remote sensing, methods for evaluation of approximation algorithms, etc., medical and biological image analysis, mesh processing, non-photorealistic rendering, and the analysis of shape in art and architecture. He is a Fellow of the International Association of Pattern Recognition (IAPR), and was awarded a place on the 1,000 Talent Plan of Foreign Experts at Nankai University (2016-2018).