Researchers have developed a standardized workflow for assessing the quality of light field media, crucial for the standardization of immersive media coding. This framework, created within JPEG Pleno standardization activities, combines benchmark generation with a hybrid subjective evaluation method that uses both reference-anchored ratings and pairwise refinement. The study also systematically evaluated a range of objective metrics, finding that while many perform well for coding-only artifacts, their accuracy decreases significantly when view synthesis distortions are introduced, highlighting the need for improved metrics in future light field quality assessments. AI
IMPACT This research provides a framework for evaluating light field media quality, which could inform the development of future immersive media coding standards.
RANK_REASON The cluster contains an academic paper detailing a new methodology and dataset for light field quality assessment. [lever_c_demoted from research: ic=1 ai=0.4]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
