PulseAugur
EN
LIVE 19:56:03

GazePrior enables zero-shot eye tracking with synthesized AR/VR data

Researchers have developed GazePrior, a novel approach for zero-shot eye tracking in AR/VR applications. This method utilizes a learned 3D prior to model human eye distributions, enabling the synthesis of realistic and diverse training data. By leveraging this synthesized data, eye tracking models achieve higher accuracy and robustness compared to existing zero-shot techniques, eliminating the need for costly real-world data collection for new devices. AI

IMPACT Enables more realistic and cost-effective AR/VR experiences by improving eye-tracking technology.

RANK_REASON The cluster contains an academic paper detailing a new method for eye tracking.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Corentin Dumery, David Colmenares, Alexander Fix, Pascal Fua, Ali Behrooz, Jogendra Kundu ·

    GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction

    arXiv:2605.22359v1 Announce Type: new Abstract: Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data gen…

  2. arXiv cs.CV TIER_1 English(EN) · Jogendra Kundu ·

    GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction

    Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data generation methods lack realism. To remove the need…