Metraipolis › archive › dc_9d40eb343be9
Diffusion models for eye-gaze trajectory generation using position and velocity representations — arXiv:2609.05522
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05522
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:06:28.664Z
- SHA-256 of the archived text
3e0caf7970e07bc7c8798339fea877fdfd0ecb386ae76c7ceaaf7eee74d8b796- Stable URL of this page
https://metraipolis.com/documento/dc_9d40eb343be9
How to cite
Diffusion models for eye-gaze trajectory generation using position and velocity representations — arXiv:2609.05522 — arXiv (en), https://arxiv.org/abs/2609.05522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9d40eb343be9 (Metraipolis archive dc_9d40eb343be9, sha256 3e0caf7970e07bc7c8798339fea877fdfd0ecb386ae76c7ceaaf7eee74d8b796)
BibTeX
@misc{dc9d40eb343be9,
title = {Diffusion models for eye-gaze trajectory generation using position and velocity representations — arXiv:2609.05522},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05522},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9d40eb343be9; sha256 3e0caf7970e07bc7c8798339fea877fdfd0ecb386ae76c7ceaaf7eee74d8b796},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints. We address this using two complementary denoising diffusion probabilistic models (DDPMs) for unconditional generation of eye-gaze dynamics from visual-search data. Both use an identical FiLM-conditioned one-dimensional U-Net with self-attention (19.35,M parameters), trained on 8,s sliding-window sequences from 28 participants. One model generates raw two-dimensional gaze-position sequences, while the other generates two-component velocity sequences; each uses representation-specific preprocessing, training settings, data partitions, and evaluation protocols. Both are evaluated across three independent training seeds, with aggregated metrics reported as mean,$\pm$,SD. The position-space model achieves a mean Jensen-Shannon (JS) divergence of $0.016\pm0.004$ across nine kinematic features, with the highest feature-wise mean below $0.030$, fixation duration within 2% of real data, and a Fr'echet Gaze Distance more than an order of magnitude below statistical and Markovian baselines. Under a Train-on-Synthetic-Test-on-Real protocol, synthetic-only training achieves $R^2=0.66\pm0.02$, or 82.7% of the real-data $R^2$ point estimate. The velocity-space model achieves a mean JS divergence of $0.0065$ across velocity components, speed, log-speed, and turning angle, with a maximum of $0.015\pm0.005$. Reconstructed path length is less accurate ($0.21\pm0.02$ versus $0.03\pm0.01$ in position space), although the protocols differ. Overall, unconditional diffusion captures local gaze kinematics and short-range temporal and directional structure, while long-range properties such as saccade counts and cumulative path geometry remain targets for future conditioned models. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.05522 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:56.968Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).