GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction

Excerpt

arXiv:2609.38519v1 Announce Type: cross Abstract: Egocentric gaze prediction enables many downstream applications but remains challenging, as human gaze is inherently stochastic. This stochasticity is constrained by structured temporal dynamics alternating between fixations and saccades, top-down influences from tasks, and bottom-up visual saliency. Based on this observation, we introduce GazeFlow, a framework that directly models gaze as a joint distribution of temporal gaze positions condition