R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment

2026-03-11

AI Summary

This study addresses the lack of systematic perceptual dimensions and interpretability in existing computer-generated (CG) image quality assessment methods. To bridge this gap, the authors define six perceptual dimensions from a user-centric perspective, construct the first dataset comprising 3,500 CG images annotated with fine-grained quality descriptions, and establish a corresponding visual question-answering benchmark. They propose a dual-stream retrieval-augmented generation framework that enhances the discriminative capability of vision-language models by retrieving semantically similar images to inform quality judgments. Experimental results demonstrate that the proposed approach significantly improves both accuracy and interpretability of CG image quality evaluation across multiple state-of-the-art vision-language models.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Immersive Computer Graphics (CGs) rendering has become ubiquitous in modern daily life. However, comprehensively evaluating CG quality remains challenging for two reasons: First, existing CG datasets lack systematic descriptions of rendering quality; and second existing CG quality assessment methods cannot provide reasonable text-based explanations. To address these issues, we first identify six key perceptual dimensions of CG quality from the user perspective and construct a dataset of 3500 CG images with corresponding quality descriptions. Each description covers CG style, content, and perceived quality along the selected dimensions. Furthermore, we use a subset of the dataset to build several question-answer benchmarks based on the descriptions in order to evaluate the responses of existing Vision Language Models (VLMs). We find that current VLMs are not sufficiently accurate in judging fine-grained CG quality, but that descriptions of visually similar images can significantly improve a VLM's understanding of a given CG image. Motivated by this observation, we adopt retrieval-augmented generation and propose a two-stream retrieval framework that effectively enhances the CG quality assessment capabilities of VLMs. Experiments on several representative VLMs demonstrate that our method substantially improves their performance on CG quality assessment.

Problem

• Computer Graphics
• Image Quality Assessment
• Vision Language Models
• Rendering Quality
• Text-based Explanation

Innovation

• Retrieval-augmented generation
• Vision Language Models
• Computer Graphics Quality Assessment
• Perceptual dimensions
• Image-text benchmark