Deep Local and Global Spatiotemporal Feature Aggregation for Blind Video Quality Assessment

TL;DR

This paper introduces DeepSTQ, a no-reference video quality assessment method that leverages pre-trained deep models to extract and aggregate local and global spatiotemporal features, outperforming existing algorithms.

Contribution

It proposes a novel deep learning-based VQA approach using pre-trained models for feature extraction without training from scratch.

Findings

DeepSTQ outperforms state-of-the-art VQA algorithms.

Utilizes pre-trained models for efficient feature extraction.

Effective in assessing various distorted videos.

Abstract

In recent years, deep learning has achieved promising success for multimedia quality assessment, especially for image quality assessment (IQA). However, since there exist more complex temporal characteristics in videos, very little work has been done on video quality assessment (VQA) by exploiting powerful deep convolutional neural networks (DCNNs). In this paper, we propose an efficient VQA method named Deep SpatioTemporal video Quality assessor (DeepSTQ) to predict the perceptual quality of various distorted videos in a no-reference manner. In the proposed DeepSTQ, we first extract local and global spatiotemporal features by pre-trained deep learning models without fine-tuning or training from scratch. The composited features consider distorted video frames as well as frame difference maps from both global and local views. Then, the feature aggregation is conducted by the regression model to predict the perceptual video quality. Finally, experimental results demonstrate that our proposed DeepSTQ outperforms state-of-the-art quality assessment algorithms.