ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction

TL;DR

The paper introduces GREED, a novel video quality assessment model that analyzes space-time entropic differences to accurately predict perceived quality across diverse frame rates, including high frame rate videos.

Contribution

GREED is the first model to effectively incorporate space-time entropic differences for frame rate dependent VQA, achieving state-of-the-art results on HFR datasets.

Findings

GREED outperforms existing VQA models on the LIVE-YT-HFR database.

Features in GREED generalize well to standard VQA datasets.

GREED effectively captures quality variations due to frame rate and compression.

Abstract

We consider the problem of conducting frame rate dependent video quality assessment (VQA) on videos of diverse frame rates, including high frame rate (HFR) videos. More generally, we study how perceptual quality is affected by frame rate, and how frame rate and compression combine to affect perceived quality. We devise an objective VQA model called Space-Time GeneRalized Entropic Difference (GREED) which analyzes the statistics of spatial and temporal band-pass video coefficients. A generalized Gaussian distribution (GGD) is used to model band-pass responses, while entropy variations between reference and distorted videos under the GGD model are used to capture video quality variations arising from frame rate changes. The entropic differences are calculated across multiple temporal and spatial subbands, and merged using a learned regressor. We show through extensive experiments that GREED achieves state-of-the-art performance on the LIVE-YT-HFR Database when compared with existing VQA models. The features used in GREED are highly generalizable and obtain competitive performance even on standard, non-HFR VQA databases. The implementation of GREED has been made available online: https://github.com/pavancm/GREED