Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble
This addresses the challenge of automated quality evaluation for AR experiences, which is important for AR developers and users, though it appears incremental as it applies existing VLMs to a new domain.
The study evaluated three commercial vision-language models (GPT, Gemini, Claude) for automated assessment of AR-generated scenes using the DiverseAR dataset, finding they achieved up to 93% true positive rate for perception and 71% for description but struggled with seamlessly integrated content.
Augmented Reality (AR) enhances the real world by integrating virtual content, yet ensuring the quality, usability, and safety of AR experiences presents significant challenges. Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? Could Vision-Language Models (VLMs) offer a solution for the automated evaluation of AR-generated scenes? In this study, we evaluate the capabilities of three state-of-the-art commercial VLMs -- GPT, Gemini, and Claude -- in identifying and describing AR scenes. For this purpose, we use DiverseAR, the first AR dataset specifically designed to assess VLMs' ability to analyze virtual content across a wide range of AR scene complexities. Our findings demonstrate that VLMs are generally capable of perceiving and describing AR scenes, achieving a True Positive Rate (TPR) of up to 93% for perception and 71% for description. While they excel at identifying obvious virtual objects, such as a glowing apple, they struggle when faced with seamlessly integrated content, such as a virtual pot with realistic shadows. Our results highlight both the strengths and the limitations of VLMs in understanding AR scenarios. We identify key factors affecting VLM performance, including virtual content placement, rendering quality, and physical plausibility. This study underscores the potential of VLMs as tools for evaluating the quality of AR experiences.