Visual Quality Assessment (A05)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: from 2015 to 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 251654672

Visual quality assessment provides indicators of perceived value of media items and allows codec developers and content providers to optimize the performance of their methods and services. In this project, we work on establishing scalable, in-the-wild crowdsourcing techniques that can replace the de facto lab based quality assessment methodology. We establish very large benchmarks and make use of them to develop deep learning methods for algorithmic visual quality assessment for images and video sequences. We apply these methods to subjective quality-aware image enhancement and perceptual evaluation of fundamental algorithms in computer vision.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 161: Quantitative Methods for Visual Computing
• Applicant Institution: Universität Stuttgart
• Project Head: Professor Dr. Dietmar Saupe