MMCVIVOct 26, 2020

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

arXiv:2010.13715v256 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses video quality assessment for diverse frame rates, which is important for video streaming and compression applications, but it is incremental as it builds on existing statistical modeling approaches.

The authors tackled the problem of predicting video quality across varying frame rates, including high frame rate videos, by developing ST-GREED, a model that uses generalized Gaussian distributions and entropy differences to analyze spatial and temporal coefficients. They showed that GREED achieves state-of-the-art performance on the LIVE-YT-HFR Database and is competitive on standard VQA databases.

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

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes