DiffGaze: A Diffusion Model for Modelling Fine-grained Human Gaze Behaviour on 360 \({}^{\circ}\) Images
ACM Transactions on Interactive Intelligent Systems · 31.03.2026 · 16 (1) · 1-23
DOI: 10.1145/3772075 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Interactive Intelligent Systems, online erschienen am 09.01.2026. Verfasst von Chuhan Jiao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: European Union’s Horizon Europe research and innovation funding programme, Deutsche Forschungsgemeinschaft, Swiss National Science Foundation.
Abstract (Originalsprache)
Modelling human gaze behaviour on 360 \({}^{\circ}\) images is important for various human–computer interaction applications. However, existing methods are limited to predicting discrete fixation sequences or aggregated saliency maps, thereby neglecting fine-grained gaze behaviour such as saccadic eye movements that can be captured by commercial eye-trackers. We introduce a more challenging task— fine-grained gaze sequence generation . This task aims to generate eye-tracker-like gaze data for given stimuli. We propose DiffGaze , a diffusion-based method for generating realistic and diverse fine-grained human gaze sequences conditioned on 360 \({}^{\circ}\) images. We evaluate DiffGaze on two 360 \({}^{\circ}\) image benchmarks for fine-grained gaze sequence generation as well as two downstream tasks, scanpath prediction and saliency prediction. Our evaluations show that DiffGaze outperforms the fine-grained gaze generation baselines in all tasks on both benchmarks. We also report a 21-participant survey study showing that our method generates gaze sequences that are indistinguishable from real human sequences. Taken together, our evaluations not only demonstrate the effectiveness of DiffGaze but also point towards a new generation of methods that faithfully model the rich spatial and temporal nature of natural human gaze behaviour.
Förderung
- European Union’s Horizon Europe research and innovation funding programme
- Deutsche Forschungsgemeinschaft
- Swiss National Science Foundation
Zitieren
APA
Jiao, C., Wang, Y., Zhang, G., Bâce, M., Hu, Z., & Bulling, A. (2026). DiffGaze: A Diffusion Model for Modelling Fine-grained Human Gaze Behaviour on 360 \({}^{\circ}\) Images. ACM Transactions on Interactive Intelligent Systems, 16(1), 1-23. https://doi.org/10.1145/3772075
Vancouver
Jiao C, Wang Y, Zhang G, Bâce M, Hu Z, Bulling A. DiffGaze: A Diffusion Model for Modelling Fine-grained Human Gaze Behaviour on 360 \({}^{\circ}\) Images. ACM Transactions on Interactive Intelligent Systems. 2026;16(1):1-23. doi:10.1145/3772075
BibTeX
@article{Jiao2026,
author = {Jiao, Chuhan and Wang, Yao and Zhang, Guanhua and Bâce, Mihai and Hu, Zhiming and Bulling, Andreas},
title = {DiffGaze: A Diffusion Model for Modelling Fine-grained Human Gaze Behaviour on 360 \(^\circ\) Images},
journal = {ACM Transactions on Interactive Intelligent Systems},
year = {2026},
volume = {16},
number = {1},
pages = {1--23},
doi = {10.1145/3772075}
}
EUVIMED