On the benefit of parameter-driven approaches for the modeling and the prediction of Satisfied User Ratio for compressed video

TL;DR

This paper introduces a novel parameter-driven approach for modeling and predicting the Satisfied-User-Ratio (SUR) curve in video compression, improving accuracy over traditional Gaussian-based methods by utilizing video features.

Contribution

It proposes a new parameter-driven method for SUR prediction and compares models using source-only and combined source plus compressed video features.

Findings

The proposed method outperforms Gaussian assumption-based models.

Video features significantly improve SUR prediction accuracy.

Source plus compressed video features yield better results than source-only features.

Abstract

The human eye cannot perceive small pixel changes in images or videos until a certain threshold of distortion. In the context of video compression, Just Noticeable Difference (JND) is the smallest distortion level from which the human eye can perceive the difference between reference video and the distorted/compressed one. Satisfied-User-Ratio (SUR) curve is the complementary cumulative distribution function of the individual JNDs of a viewer group. However, most of the previous works predict each point in SUR curve by using features both from source video and from compressed videos with assumption that the group-based JND annotations follow Gaussian distribution, which is neither practical nor accurate. In this work, we firstly compared various common functions for SUR curve modeling. Afterwards, we proposed a novel parameter-driven method to predict the video-wise SUR from video features. Besides, we compared the prediction results of source-only features based (SRC-based) models and source plus compressed videos features (SRC+PVS-based) models.