报 告 人：A. Murat Tekalp 院士

工作单位：科奇大学（土耳其）

报告题目：图像/视频超分辨率及压缩的生成模型

报告时间：2023年5月20日（周六）14:30-15:30

报告链接：Teams Link

https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d

内容摘要：

  利用回归模型最小化图像/视频超分辨率（SR）和变分自动编码器（VAE）的失真度量，以最小化图像/视频压缩任务的速率失真损失是目前常用的方法。虽然生成模型，如GANs和流模型，已经用于感知图像/视频SR和压缩，但它们有局限性，如训练的收敛性和稳定性。近年来，扩散模型在不同的图像/视频合成应用中非常流行。本报告将讨论像素空间和特征空间（稳定）扩散模型在感知图像/视频SR和压缩任务中可能的应用，并比较它们与稳定GAN模型训练方法的优缺点。

个人简介：

  A. Murat Tekalp 教授（IEEE研究员）于1984年在美国纽约州特洛伊市伦斯勒理工学院 (RPI) 获得博士学位，1984年至1987年间在纽约罗切斯特的伊士曼柯达公司工作，1987年至2005年间在罗切斯特大学工作，并被提升为杰出大学教授。A. Murat Tekalp目前是土耳其伊斯坦布尔科奇大学的教授，曾在2010年至2013年间担任工程学院院长。A. Murat Tekalp的研究方向是数字图像和视频处理，包括视频压缩和流式传输、视频网络、多视图和3-D视频处理，以及用于图像视频处理和压缩的深度学习。A. Murat Tekalp当选为土耳其科学院和欧洲科学院院士，曾担任 IEEE 信号处理汇刊 (1990–1992) 和IEEE图像处理汇刊 (1994–1996) 的副主编，在1999年至2010年间担任由Elsevier出版的EURASIP期刊Signal Processing: Image Communications 的主编，是IEEE Signal Processing杂志 (2007-2010) 和 Proceedings of the IEEE的编辑委员会成员（2014-2020）。A. Murat Tekalp教授于1996年1月至1997年12月期间担任IEEE信号处理协会图像和多维信号处理技术委员会主席，于2002年被任命为美国纽约州罗切斯特市 IEEE 国际图像处理会议 (ICIP) 的总主席以及IEEE ICIP 2020和ICIP 2024技术计划联合主席，曾在欧洲研究委员会 (ERC) 高级拨款小组（2009-2015年）和启动拨款小组（2021年）中任职。A. Murat Tekalp于1995年出版专著《Digital Video Processing》，该书的第二版全面重编后于2015年出版。

【编辑：王健】

英文版：

Academic Report Notice of A. Murat Tekalp : Generative Models for Image/Video Super-resolution and Compression

Speaker: Academician  A.  Murat Tekalp

Title: Generative Models for Image/Video Super-resolution and Compression

Time: 14:30 pm, May 20, 2023 (Saturday)

Link: https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d

Abstract:

   It is common practice to use regressive models that minimize a measure of distortion for image/video super resolution (SR) and variational auto-encoders (VAE) to minimize rate distortion loss for image/video compression tasks. Although generative models, such as GANs and flow models, have been previously used for perceptual image/video SR and compression, they have limitations such as convergence and stability of training. Recenty, diffusion models have become very popular for different image/video synthesis applications. This talk discusses possible use of pixel space and feature space (stable) diffusion models for perceptual image/video SR and compression tasks and compares their advantages an d disadvantage vs. stable GAN model training approaches.

Personal Introduction: 

   A. Murat Tekalp (Fellow, IEEE) received the Ph.D. degree in electrical, computer, and systems engineering from Rensselaer Polytechnic Institute (RPI), Troy, NY, USA, in 1984. He was with Eastman Kodak Company, Rochester, New York, from 1984 to 1987, and with the University of Rochester, Rochester, New York, from 1987 to 2005, where he was promoted to Distinguished University Professor. He is currently a Professor with Koc University, Istanbul, Turkey. He served as the Dean of Engineering between 2010 and 2013. His research interests are in digital image and video processing, including video compression and streaming, video networking, multi-view and 3-D video processing, and deep learning for image video processing and compression. He has been elected a member of Turkish Academy of Sciences and Academia Europaea. He served as an Associate Editor for the IEEE Transactions on Signal Processing (1990–1992) and IEEE Transactions on Image Processing (1994–1996). He was the Editor-in-Chief for the EURASIP journal Signal Processing: Image Communication published by Elsevier between 1999 and 2010. He was on the Editorial Board for the IEEE Signal Processing Magazine (2007–2010) and the Proceedings of the IEEE (2014–2020). He chaired the IEEE Signal Processing Society Technical Committee on Image and Multidimensional Signal Processing (January 1996–December 1997). He was appointed as the General Chair of IEEE International Conference on Image Processing (ICIP), Rochester, NY, USA, in 2002 and the Technical Program Co-Chair for IEEE ICIP 2020 and ICIP 2024. He served in the European Research Council (ERC) Advanced Grant Panels (2009–2015) and Starting Grant Panel in 2021. He is currently on the Editorial Board of Wiley-IEEE Press.  He has authored the Prentice Hall book Digital Video Processing (1995), a completely rewritten second edition of which is published in 2015.

                                                                                                                                                         [Editor: Jian Wang]