ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images

TL;DR

This paper introduces ViDA-UGC, a large-scale dataset and benchmark for detailed, explainable image quality assessment of user-generated content, leveraging human annotations and GPT-4o for fine-grained distortion analysis.

Contribution

It presents the first comprehensive UGC distortion assessment dataset and benchmark, enabling improved explainable IQA through a novel Chain-of-Thought framework and human-verified annotations.

Findings

ViDA-UGC improves image quality analysis across multiple models.

The Chain-of-Thought framework enhances distortion detection accuracy.

Models trained on ViDA-UGC outperform existing benchmarks.

Abstract

Recent advances in Multimodal Large Language Models (MLLMs) have introduced a paradigm shift for Image Quality Assessment (IQA) from unexplainable image quality scoring to explainable IQA, demonstrating practical applications like quality control and optimization guidance. However, current explainable IQA methods not only inadequately use the same distortion criteria to evaluate both User-Generated Content (UGC) and AI-Generated Content (AIGC) images, but also lack detailed quality analysis for monitoring image quality and guiding image restoration. In this study, we establish the first large-scale Visual Distortion Assessment Instruction Tuning Dataset for UGC images, termed ViDA-UGC, which comprises 11K images with fine-grained quality grounding, detailed quality perception, and reasoning quality description data. This dataset is constructed through a distortion-oriented pipeline, which involves human subject annotation and a Chain-of-Thought (CoT) assessment framework. This framework guides GPT-4o to generate quality descriptions by identifying and analyzing UGC distortions, which helps capturing rich low-level visual features that inherently correlate with distortion patterns. Moreover, we carefully select 476 images with corresponding 6,149 question answer pairs from ViDA-UGC and invite a professional team to ensure the accuracy and quality of GPT-generated information. The selected and revised data further contribute to the first UGC distortion assessment benchmark, termed ViDA-UGC-Bench. Experimental results demonstrate the effectiveness of the ViDA-UGC and CoT framework for consistently enhancing various image quality analysis abilities across multiple base MLLMs on ViDA-UGC-Bench and Q-Bench, even surpassing GPT-4o.