Patch-VQ: 'Patching Up' the Video Quality Problem

TL;DR

This paper introduces a large-scale real-world video quality dataset and two novel no-reference VQA models, achieving state-of-the-art results and enabling better localization of perceptual distortions in user-generated videos.

Contribution

It presents the largest real-world UGC video quality dataset and two innovative NR-VQA models, advancing the accuracy and interpretability of video quality assessment.

Findings

PVQ achieves state-of-the-art performance on 3 UGC datasets.

The dataset contains 39,000 videos and 5.5 million annotations.

PVQ Mapper effectively localizes perceptual distortions.

Abstract

No-reference (NR) perceptual video quality assessment (VQA) is a complex, unsolved, and important problem to social and streaming media applications. Efficient and accurate video quality predictors are needed to monitor and guide the processing of billions of shared, often imperfect, user-generated content (UGC). Unfortunately, current NR models are limited in their prediction capabilities on real-world, "in-the-wild" UGC video data. To advance progress on this problem, we created the largest (by far) subjective video quality dataset, containing 39, 000 realworld distorted videos and 117, 000 space-time localized video patches ('v-patches'), and 5.5M human perceptual quality annotations. Using this, we created two unique NR-VQA models: (a) a local-to-global region-based NR VQA architecture (called PVQ) that learns to predict global video quality and achieves state-of-the-art performance on 3 UGC datasets, and (b) a first-of-a-kind space-time video quality mapping engine (called PVQ Mapper) that helps localize and visualize perceptual distortions in space and time. We will make the new database and prediction models available immediately following the review process.