VRBiom: A New Periocular Dataset for Biometric Applications of HMD

TL;DR

This paper introduces VRBiom, the first public dataset of periocular videos captured with a consumer head-mounted display that provides non-frontal eye views. It combines 900 bona-fide videos from 25 subjects with approximately 1100 presentation-attack videos across 92 attack instruments, using three gaze conditions and eyewear variations in the NIR spectrum at 400×400 resolution and 72 FPS. The dataset supports iris/periocular recognition, presentation-attack detection, and eye-region semantic segmentation, highlighting realistic challenges such as non-frontal viewpoints, low resolution, and hardware constraints. By offering a real-world VR/AR biometric resource, VRBiom facilitates benchmarking, domain adaptation, and the development of robust authentication and segmentation methods for HMD-based applications.

Abstract

With advancements in hardware, high-quality HMD devices are being developed by numerous companies, driving increased consumer interest in AR, VR, and MR applications. In this work, we present a new dataset, called VRBiom, of periocular videos acquired using a Virtual Reality headset. The VRBiom, targeted at biometric applications, consists of 900 short videos acquired from 25 individuals recorded in the NIR spectrum. These 10s long videos have been captured using the internal tracking cameras of Meta Quest Pro at 72 FPS. To encompass real-world variations, the dataset includes recordings under three gaze conditions: steady, moving, and partially closed eyes. We have also ensured an equal split of recordings without and with glasses to facilitate the analysis of eye-wear. These videos, characterized by non-frontal views of the eye and relatively low spatial resolutions (400 x 400), can be instrumental in advancing state-of-the-art research across various biometric applications. The VRBiom dataset can be utilized to evaluate, train, or adapt models for biometric use-cases such as iris and/or periocular recognition and associated sub-tasks such as detection and semantic segmentation. In addition to data from real individuals, we have included around 1100 PA constructed from 92 PA instruments. These PAIs fall into six categories constructed through combinations of print attacks (real and synthetic identities), fake 3D eyeballs, plastic eyes, and various types of masks and mannequins. These PA videos, combined with genuine (bona-fide) data, can be utilized to address concerns related to spoofing, which is a significant threat if these devices are to be used for authentication. The VRBiom dataset is publicly available for research purposes related to biometric applications only.

Figures (4)

• Figure 1: Examples of biometric use-cases offered by the HMD data, in particular by the VRBiom dataset (The example images are obtained from 9107939wang2021nirhoffman2019iris).
• Figure 2: Setup for the dataset collections: (a) for bona-fide recordings, the subjects wore the HMD devices, (b) for PA recordings, the HMD device was carefully placed on the temple region of the attack instrument (mannequin, in this example), and (c) the Meta Quest Pro Data Capture App used for data collection.
• Figure 3: Samples of bona-fide recordings from VRBiom dataset. Each row presents a sample of steady gaze, moving gaze, and partially closed eyes (from left to right). Top and bottom rows refer to recordings without and with glasses, respectively.
• Figure 4: Samples of PA recordings from VRBiom. The top row represents the PAI captured in RGB (visible) spectrum, while middle and bottom rows depict the NIR recordings without and with glasses, respectively, as acquired by the internal (right) camera of the Meta Quest Pro. From left to right, each column presents a sample of the type of PAIs belonging to the attack series from 2--7.