内容

龚明伦教授:Two Routes for Image-to-Image Translation: Rule-based vs. Learning-based

阅读数:323    发布:2018-09-19 08:58    

主题: Two Routes for Image-to-Image Translation: Rule-based vs. Learning-based

主讲人:龚明伦

时间:9月20日10:30am-11:30am

地点:计算机与软件学院938会议室

Abstract

Many image processing and computer vision tasks, such as image segmentation, stylization, and abstraction, can be posed as image-to-image translation problems.  This talk presents two different image-to-image translation approaches, one is rule-base and the other is learning-based. The rule-based algorithm is capable of stylizing an input face photo using a single exemplar image.  Since the numbers and varieties of patch samples are highly limited, special cares are put into sample selection to best preserve the identity and content of the input face.  A two-phase procedure is also designed, where colors are transferred first in a semantic-aware manner, followed by edge-preserving texture transfer. The learning-based algorithm employs Conditional Generative Adversarial Networks (GANs) to perform general cross-domain image-to-image translation.  It requires a large set of training images, but unlike existing approaches, the images do not need to be labeled.  To train in an unsupervised manner, two GANs are constructed to translate images in opposite directions, forming a closed loop.  As a result, images from either domain can be translated to the other and then reconstructed, enabling a reconstruction error term for training. 

Dr. Minglun Gong is a Professor and Head at the Department of Computer Science, Memorial University of Newfoundland and an adjunct professor at the University of Alberta. He obtained his Ph.D. from the University of Alberta in 2003, his M.Sc. from the Tsinghua University in 1997, and his B.Engr. from the Harbin Engineering University in 1994. After graduation, he was a faculty member at the Laurentian University for four years before joined the Memorial University. Minglun’s research interests cover various topics in the broad area of visual computing (including computer graphics, computer vision, visualization, image processing, and pattern recognition). So far, he has published over 100 referred technical papers in journals and conference proceedings, including 18 articles in ACM/IEEE transactions. He is the inventor of an awarded patent and 3 pending patents. Currently an associate editor for Pattern Recognition, he has also served as program committee member for top-tier conferences (e.g. ICCV and CVPR) and reviewer for prestigious journals (e.g. IEEE TPAMI and ACM TOG). He was the recipient of the Izaak Walton Killam Memorial Award and the CFI New Opportunity Award.


深圳大学计算机与软件学院 2009-2016