Description
The purpose of this workshop is to discuss current challenges and unsolved issues in image quality assessment. These presentations will act as inspiration to facilitate dialogue and discussions with the participants.
Presentations
- Challenges of quality assessment in immersive technologies, Chaker Larabi, Université de Poitiers (France)
- Computational vs engineering image quality metrics: advantages, disadvantages, and a way forward, Sophie Triantaphillidou, University of Westminister (UK)
- Currents trends in statistical analysis of subjective and objective image quality assessment, Dietmar Saupe, Universität Konstanz (Germany)
- Challenges in image/video quality assessment in mobile devices, François-Xavier Thomas, DxOMark (France)
- The impact of observer demographics on image quality ratings, Simon Hviid Del Pin, NTNU (Norway)
- Rethinking image quality assessment: how AI paradigm is reshaping image quality assessment, Azeddine Beghdadi (University Sorbonne Paris Nord (France)
The workshop is sponsored by the Research Council of Norway through the project “Quality and Content: understanding the influence of content on subjective and objective image quality assessment” grant number 324663 and the project “VQ4MedicS: Video Quality Assessment and Enhancement for Pre-Hospital Medical Services” grant number 329034.
Speakers
Azeddine Beghdadi is a full professor (Exceptional Class) at University Sorbonne Paris Nord. He is the founding member of the Laboratory of Information Processing and Transmission (L2TI laboratory) and served as its director from 2010 to 2016. Beghdadi is the founder and steering committee chair of the European Workshop on Visual Information Processing (EUVIP). He holds a PhD in optics and signal processing from Sorbonne University Pierre and Marie Curie, has co-authored more than 350 papers, including 6 best paper awards, given more than 30 invited and plenary talks; and supervised more than 40 PhD/Post-doc students. His research interests include image/video quality enhancement and assessment, computational visual perception models for image/ video processing and scene understanding and medical imaging. He serves as and AE on related professional journals.
more
Simon H. Del Pin holds an MSc in psychology with a focus on cognitive neuroscience from Aalborg University (2013) and a PhD with distinction from Jagiellonian University. He has made contributions to the fields of consciousness and cognitive neuroscience. His research has delved into the intricacies of subjective experiences and the assessment of visual quality in digital media. He has presented his work at conferences, received grants and fellowships, and published numerous papers in respected journals, working to contribute to our understanding of consciousness and perception.
more
Mohamed-Chaker Larabi holds a PhD from Université de Poitiers, where he is currently an associate professor and the deputy scientific director of the GdR-ISIS (French Research Group on Signal and Image Processing). He has supervised more than 20 PhD students and published more than 200 papers. His research interests include quality of experience and bio-inspired processing/coding/optimization of images and videos, such as 2-D, 3-D, HDR, and 360/VR/AR/MR. He participates in a number of standards committees, has chaired many conferences, and is an associate editor for six journals.
more
Dietmar Saupe has a Dr.rer.nat. in mathematics from the University of Bremen and is a full professor for computer science at the University of Konstanz (Germany). He heads a research group focusing on multimedia signal processing including applications in sports science; currently the group is mainly engaged in a project on image and video quality assessment. His areas of interest have included numerical methods, dynamical systems, scientific visualization, computer graphics, image and video compression, medical image processing, computer vision, 3D models, and sports informatics.
more
François-Xavier Thomas is an engineer at DXOMARK Image Labs working in designing lab protocols and measurement software to quantify imaging systems performance. He is part of the team of engineers building the Analyzer suite of hardware and software tools used internally by DXOMARK, as well as by imaging labs in other companies worldwide, to assess the performance of camera systems. He holds an MSc in computer science, image and signal processing from Télécom ParisTech and is particularly active in the topics of geometrical/distortion calibration, noise and color science, as well as HDR technologies.
more
Sophie Triantaphillidou is a professor emerita in Imaging Science at the University of Westminster, where she led the Computational Vision and Imaging Technology research group for 15 years. She holds a PhD in imaging science. Her research is interdisciplinary, exploring interrelationships between imaging system performance and image quality, image content, and image perception by human and machine vision systems. She has led numerous research collaborations with academic, government, and industry participants and is the recipient of several research awards, including the RPS Davies Medal for “significant contribution to digital imaging science”.
more