Abstract
Just Noticeable Difference (JND) establishes the threshold between two images or videos wherein differences in quality remain imperceptible to an individual. This threshold, collectively known as the Satisfied User Ratio (SUR), holds significant importance in image and video compression applications, ensuring that differences in quality are imperceptible to the majority (p%) of users, known as p%SUR. While substantial efforts have been dedicated to predicting the p%SUR for various encoding parameters (e.g., QP) and quality metrics (e.g., VMAF), referred to as proxies, systematic consideration of the prediction uncertainties associated with these proxies has hitherto remained unexplored. In this paper, we analyze the uncertainty of p%SUR through Confidence Interval (CI) estimation and assess the consistency of various Video Quality Metrics (VQMs) as proxies for SUR. The analysis reveals challenges in directly using p%SUR as ground truth for training models and highlights the need for uncertainty estimation for SUR with different proxies.
Originalsprache | Englisch |
---|---|
Titel | 2024 Picture Coding Symposium (PCS) |
Seitenumfang | 5 |
ISBN (elektronisch) | 979-8-3503-5848-3 |
DOIs | |
Publikationsstatus | Veröffentlicht - 26 Juni 2024 |
Veranstaltung | PCS 2024. Picture Coding Symposium - Taichung, Taiwan Dauer: 12 Juni 2024 → 14 Juni 2024 https://2024.picturecodingsymposium.org/ |
Publikationsreihe
Name | 2024 Picture Coding Symposium, PCS 2024 - Proceedings |
---|
Konferenz
Konferenz | PCS 2024. Picture Coding Symposium |
---|---|
Kurztitel | PCS 2024 |
Land/Gebiet | Taiwan |
Stadt | Taichung |
Zeitraum | 12/06/24 → 14/06/24 |
Internetadresse |
Research Field
- Former Research Field - Human-centered Automation and Assistance