arXiv · 2609.38519
GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction
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 conditioned upon both top-down and bottom-up information. In particular, GazeFlow uses conditional flow matching (CFM): a learned velocity field iteratively transports a Gaussian noise sample into a plausible gaze trajectory drawn from this joint distribution. The velocity field is conditioned on bottom-up visual features extracted by a video encoder and on top-down task information obtained by globally querying these features. On standard datasets, GazeFlow achieves state-of-the-art performance on per-frame metrics, and the generated trajectories align better with human gaze temporal dynamics.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Sheng Zhao, Weikai Lin, Yuhao Zhu. 2026-09-29. GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction. https://searcharxiv.com/abs/2609.38519
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.