Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment

TL;DR

This paper introduces a no-reference video quality assessment method that learns generalized spatial-temporal features, effectively handling variations in content, resolution, and frame rate to improve cross-dataset prediction accuracy.

Contribution

The paper proposes a novel spatial-temporal feature learning approach with Gaussian distribution constraints and a pyramid temporal aggregation module for enhanced generalization.

Findings

Outperforms state-of-the-art methods in cross-dataset evaluations

Achieves comparable performance on intra-dataset tests

Demonstrates high generalization capability across diverse video qualities

Abstract

In this work, we propose a no-reference video quality assessment method, aiming to achieve high-generalization capability in cross-content, -resolution and -frame rate quality prediction. In particular, we evaluate the quality of a video by learning effective feature representations in spatial-temporal domain. In the spatial domain, to tackle the resolution and content variations, we impose the Gaussian distribution constraints on the quality features. The unified distribution can significantly reduce the domain gap between different video samples, resulting in a more generalized quality feature representation. Along the temporal dimension, inspired by the mechanism of visual perception, we propose a pyramid temporal aggregation module by involving the short-term and long-term memory to aggregate the frame-level quality. Experiments show that our method outperforms the state-of-the-art methods on cross-dataset settings, and achieves comparable performance on intra-dataset configurations, demonstrating the high-generalization capability of the proposed method.