Learning Quality from Complexity and Structure: A Feature-Fused XGBoost Model for Video Quality Assessment

TL;DR

This paper introduces a lightweight, interpretable XGBoost-based model that combines complexity and structural features for effective, real-time video quality assessment without deep learning, suitable for streaming applications.

Contribution

It proposes a novel reduced-reference VQA method using feature fusion from complexity and structure, trained with XGBoost, avoiding deep neural networks.

Findings

Achieves competitive correlation with subjective scores

Requires no GPU or deep learning models

Demonstrates strong generalization on challenge dataset

Abstract

This paper presents a novel approach for reduced-reference video quality assessment (VQA), developed as part of the recent VQA Grand Challenge. Our method leverages low-level complexity and structural information from reference and test videos to predict perceptual quality scores. Specifically, we extract spatio-temporal features using Video Complexity Analyzer (VCA) and compute SSIM values from the test video to capture both texture and structural characteristics. These features are aggregated through temporal pooling, and residual features are calculated by comparing the original and distorted feature sets. The combined features are used to train an XGBoost regression model that estimates the overall video quality. The pipeline is fully automated, interpretable, and highly scalable, requiring no deep neural networks or GPU inference. Experimental results on the challenge dataset demonstrate that our proposed method achieves competitive correlation with subjective quality scores while maintaining a low computational footprint. The model's lightweight design and strong generalization performance suit real-time streaming quality monitoring and adaptive encoding scenarios.