Summary: Interactive game streaming introduces distinct challenges for video compression and perceptual optimization due to the highly dynamic nature of gaming content, the multimodal experience, and the stringent latency requirements. These characteristics motivate encoding strategies that adapt to spatial and temporal variations in scene complexity while operating under tight bitrate constraints. This talk presents research on content-adaptive encoding for interactive game streaming. Lightweight learning-based methods are investigated to guide video rate–distortion optimisation by incorporating content characteristics into practical encoding pipelines. The objective is to improve coding efficiency through more informed bit allocation without introducing additional system overhead. In addition, open challenges in the assessment of quality of experience for interactive game streaming are discussed.
Challenges of Interactive Game Streaming at Scale
Life Sciences Building- room G13/14,Tyndall Avenue, BS8 1TQ
Bio: Angeliki Katsenou is a Manager in ML, in the Visual Computing Group, Sony Interactive Entertainment (PlayStation). She received the Diploma in Electrical and Computer Engineering and the M.Sc. degree in Signal and Image Processing from the University of Patras, Greece, and the Ph.D. degree (2014) from the Department of Computer Science and Engineering, University of Ioannina. From 2015 to 2025, she held several academic positions such as Senior Research Fellow and Senior Lecturer with the University of Bristol, U.K. and as Assistant Professor with Trinity College Dublin, Ireland. Her research interests span the media communications pipeline—analysis, compression, and communication—with emphasis on perceptual video quality assessment and sustainability/energy-aware media processing.