ImmerIris: A Large-Scale Dataset and Benchmark for Immersive Iris Recognition in Open Scenes

2025-10-11

AI Summary

To address perspective distortion, image quality degradation, and intra-class texture variation in off-axis iris recognition for immersive AR/VR scenarios, this paper introduces ImmerIris—the first large-scale, open-scene VR headset-captured iris dataset (499,791 eye images)—and establishes a multi-factor evaluation benchmark. We propose an end-to-end recognition paradigm that eliminates conventional iris normalization, instead leveraging a deep learning framework with minimal preprocessing to directly learn discriminative off-axis iris features. Our method significantly enhances robustness under large viewpoint variations and degraded image quality. Extensive experiments on ImmerIris consistently outperform the traditional two-stage pipeline (normalization followed by feature extraction), demonstrating superior accuracy and generalizability in realistic, complex immersive environments. This work advances the state of the art in unconstrained iris recognition for next-generation wearable XR systems.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In egocentric applications such as augmented and virtual reality, immersive iris recognition is emerging as an accurate and seamless way to identify persons. While classic systems acquire iris images on-axis, i.e., via dedicated frontal sensors in controlled settings, the immersive setup primarily captures off-axis irises through tilt-placed headset cameras, with only mild control in open scenes. This yields unique challenges, including perspective distortion, intensified quality degradations, and intra-class variations in iris texture. Datasets capturing these challenges remain scarce. To fill this gap, this paper introduces ImmerIris, a large-scale dataset collected via VR headsets, containing 499,791 ocular images from 564 subjects. It is, to the best of current knowledge, the largest public dataset and among the first dedicated to off-axis acquisition. Based on ImmerIris, evaluation protocols are constructed to benchmark recognition methods under different challenging factors. Current methods, primarily designed for classic on-axis imagery, perform unsatisfactorily on the immersive setup, mainly due to reliance on fallible normalization. To this end, this paper further proposes a normalization-free paradigm that directly learns from ocular images with minimal adjustment. Despite its simplicity, this approach consistently outperforms normalization-based counterparts, pointing to a promising direction for robust immersive recognition.

Problem

• Addressing iris recognition challenges in immersive VR/AR environments
• Overcoming perspective distortion and quality degradation in off-axis acquisition
• Developing normalization-free methods for robust open-scene iris recognition

Innovation

• Large-scale VR headset dataset for off-axis iris recognition
• Normalization-free paradigm learning directly from ocular images
• Benchmark protocols evaluating recognition under challenging factors