Problem
Research questions and friction points this paper is trying to address.
Augmented Reality
Image Quality Assessment
Stereoscopic
Visual Confusion
Quality of Experience
ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality
🤖 AI Summary
This study addresses the limited ecological validity of existing augmented reality (AR) image quality assessment datasets, which often rely on monocular or oversimplified scenes and fail to capture visual interference between real and virtual layers. To bridge this gap, we present ARIQA-3DS, the first large-scale stereoscopic AR image quality dataset, integrating high-resolution stereoscopic 360° real-world backgrounds with diverse virtual foregrounds. Subjective quality ratings and simulator sickness metrics were collected via a video see-through head-mounted display under controlled transparency and distortion conditions. Our findings reveal that perceived quality is primarily influenced by foreground distortions and modulated by transparency levels, while oculomotor and disorientation symptoms exhibit gradual yet manageable increases. The dataset will be publicly released to establish a new benchmark for AR quality evaluation.
📝 Abstract
As Augmented Reality (AR) technologies advance towards immersive consumer adoption, the need for rigorous Quality of Experience (QoE) assessment becomes critical. However, existing datasets often lack ecological validity, relying on monocular viewing or simplified backgrounds that fail to capture the complex perceptual interplay, termed visual confusion, between real and virtual layers. To address this gap, we present ARIQA-3DS, the first large stereoscopic AR Image Quality Assessment dataset. Comprising 1,200 AR viewports, the dataset fuses high-resolution stereoscopic omnidirectional captures of real-world scenes with diverse augmented foregrounds under controlled transparency and degradation conditions. We conducted a comprehensive subjective study with 36 participants using a video see-through head-mounted display, collecting both quality ratings and simulator-sickness indicators. Our analysis reveals that perceived quality is primarily driven by foreground degradations and modulated by transparency levels, while oculomotor and disorientation symptoms show a progressive but manageable increase during viewing. ARIQA-3DS will be publicly released to serve as a comprehensive benchmark for developing next-generation AR quality assessment models.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Stereoscopic Image Quality Assessment
Augmented Reality
Visual Confusion
Ecological Validity
Subjective Quality Evaluation
🔎 Similar Papers
No similar papers found.
