SOURCE-LINKED INTELLIGENCE

Self-Supervised Multi-View 3D Gaze Target Estimation via Probabilistic Ray Marching

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

We present a self-supervised approach, Self-MVGTE, for estimating 3D gaze targets from multiple camera views. Unlike existing methods that independently estimate 2D gaze targets per camera view, Self-MVGTE predicts gaze targets directly in 3D space for the first time. Moreover, it does not require any ground-truth annotations from the target scene and uses only the multi-view input images from a calibrated camera setup, pseudo 2D gaze target labels from a monocular gaze target estimation model, and 3D gaze vectors from a monocular 3D gaze estimation model. A key challenge is that these pseudo

Read original source ↗ Open in workspace

recordType

paper

region

Global