SS4: Quality Assessment for Computer Vision Applications 

Motivation and objectives

Methods for visual quality assessment are used to estimate or mimic human judgment when rating the quality of visual media for general purpose. These methods are not necessarily appropriate when the final observer is a computer vision algorithm, notably performing a specific task (e.g: detection, segmentation, recognition tasks ...). 

Therefore, the correct estimation of video processing pipeline performance under various conditions is still a significant research challenge in Computer Vision (CV). The goal of this special session is to bring together researchers to exchange the latest advances in testing methodologies and frameworks to identify the limit of CV methods with respect to the visual quality of the ingest, minimum quality requirements and objective visual quality measures to estimate if a visual content is the operating region of CV, and metric algorithms for a specific CV task. 

Topics of interest

We are seeking papers that include, but are not limited to, the following topics:

• Quality assessment for computer vision applications:

  •  Testing methodologies and frameworks to identify the limit of CV methods concerning the visual quality of the ingest 

  • Minimum quality requirements and objective visual quality measure to estimate if visual content is the operating region of CV 

• Quality assessment for immersive media applications: 

  • Using repurposed traditional content for virtual reality 

  • New content explicitly captured for virtual reality, including 360 cameras and light field cameras 

  • Virtual reality gaming 

Organizers

• Mikołaj Leszczuk, University of Science and Technology, Kraków, Poland

• Patrick Le Callet, Nantes Université, École Centrale Nantes, Nantes, France 

• Lu Zhang, INSA Rennes/Institut d'Electronique et des Technologies du numéRique (IETR), France