VALSE Webinar 19-18期 图像质量评价:挑战与展望

报告摘要：

Image quality assessment (IQA) aims to quantify the human perception of image quality, which is a fundamental problem in image processing and computer vision. While the recent development of objective IQA is worth celebrating, many challenges remain when we apply existing IQA models in real-world applications.

In this talk, I will discuss three real-world challenges in IQA and present solutions to them: (1) Group Maximum Differentiation Competition. How to test the generalizability of objective IQA models on a large-scale image database with no human annotations? (2) Deep Learning for IQA. Is it possible to learn deep neural networks for IQA from a small number of human annotations? How to incorporate biologically plausible components to reduce network complexity? (3) Multi-Exposure Image Fusion (MEF). What is the role of IQA in such a specific image processing application? How to design better MEF methods from quality assessment to perceptual optimization? Finally, I will introduce other real-world challenges in IQA and point out some promising future directions.

参考文献：

[1] Kede Ma, Zhengfang Duanmu, Zhou Wang, Qingbo Wu, Wentao Liu, Hongwei Yong, Hongliang Li, and Lei Zhang, “Group Maximum Differentiation Competition: Model Comparison with Few Samples,” IEEE T-PAMI, 2019.

[2] Kede Ma, Wentao Liu, Kai Zhang, Zhengfang Duanmu, Zhou Wang, and Wangmeng Zuo, “End-to-End Blind Image Quality Assessment Using Deep Neural Networks,” IEEE T-IP, 2018.

[3] Kede Ma, Zhengfang Duanmu, Hojatollah Yeganeh, and Zhou Wang, “Multi-Exposure Image Fusion by Optimizing A Structural Similarity Index,” IEEE T-CI, 2018.

报告嘉宾： 吴庆波（电子科技大学）

报告时间： 2019年8月7日（星期三）晚上20:45（北京时间）

报告题目： Visual Quality Assessment-From Algorithms to Applications

报告人简介：

Qingbo Wu is an Associate Professor at the School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC). He received the Ph.D. degree in Signal and Information Processing from UESTC in 2015. Before joining the UESTC, he was a research assistant in the Chinese University of Hong Kong, and visiting scholar in the University of Waterloo. He was selected to the “Spark Program of Fundamental Research”, and “Young Scholar of Distinction” of UESTC in 2018. His research interests include the image quality assessment theory, image enhancement and restoration model, perception-driven deep neural network, etc. He has authored more than 80 scientific publications, including various IEEE Transactions and journals, and conference papers of CVPR, ECCV, ACM MM and so on. He received the Top 10% paper awards at the IEEE ICIP 2015 and VCIP 2016.