SPS Webinar: Image-to-Image Translation: Methods and Applications
Date: 25 April 2024
Time: 8:00 AM ET (New York Time)
Presenter(s): Dr. Zhibo Chen, Dr. Jianxin Lin
Original article: Download Open Access article
The original article will be made freely available for download on the day of the webinar for 48 hours.
Abstract
In recent years, we have witnessed the impressive progress of cross-modality and cross-domain content generation based on generative learning approaches. In this webinar, the presenters will introduce Image-to-image translation (I2I) technologies, which aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has gained significant traction and achieved remarkable advancements in recent years due to its extensive applicability in various computer vision and image processing tasks. These tasks include, but are not limited to, image synthesis, segmentation, style transfer, restoration, and pose estimation. Firstly, they will begin with the introduction of well-established generative models, including the VAE model, GAN model, AR model, and Diffusion model. Next, they will provide a detailed summary of Image-to-image translation technologies. The presenters will categorize the cross-domain image generation problem into two main sets of tasks, i.e., supervised cross-domain image generation tasks and unsupervised/self-supervised cross-domain image generation tasks. They will provide a detailed taxonomy of the cross-domain image generation based on the different ways of designing model architecture, model optimization and sources of information, such as few-shot image generation or multi-modal image generation. In closing, the presenters will provide a concise overview of recent progress and upcoming research directions.
Biography
Zhibo Chen (M’01-SM’11) received the B. Sc., and Ph.D. degree from department of electrical engineering, Tsinghua University, China in 1998 and 2003, respectively.
He is currently a full professor at University of Science and Technology of China. He is primarily interested in exploring artificial intelligence methods for advanced visual signal generation, representation, processing and coding, as well as in other interdisciplinary research fields.
Dr. Chen currently holds the position of Chair for the IEEE CASS Visual Signal Processing and Communications Technical Committee (VSPC-TC) and is an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology. Additionally, he has served as Corresponding Guest Editor for the IEEE Open Journal of Circuits and Systems and the IEEE Journal of Emerging and Selected Topics in Circuits and Systems. Furthermore, he has acted as the Technical Program Committee (TPC) Chair for the 2019 IEEE International Conference on Picture Coding Symposium (PCS), has been a TPC member for the IEEE International Symposium on Circuits and Systems (ISCAS) and the IEEE Visual Communications and Image Processing (VCIP) conference. He has more than 180 publications and over 100 granted patent applications. Some of his standard proposals have been adopted in MPEG/VCEG on video coding and ITU-T on video quality assessment. In 2023, he was honored with the IEEE VCIP Best Paper award.
Jianxin Lin (M’21) received the B.E. in computer science and the Ph.D. in image processing from the University of Science and Technology of China (USTC) in 2015 and 2020, respectively.
He is currently an associate professor at the School of Computer Science and Electronic Engineering, Hunan University, Changsha, China. His current research interests include image and video processing, synthesis, and understanding.
Dr. Lin has authored over 30 papers published in various conferences and journals and received the Top Paper Award at the 2022 ACM MM Conference.
