# ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling

arXiv: https://arxiv.org/abs/2606.15486 · HTML: https://mlsanity.com/paper/2606.15486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 13 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model](https://mlsanity.com/paper/1611.09571/) (2016)
- [Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet](https://mlsanity.com/paper/1411.1045/) (2014)
- [DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling](https://mlsanity.com/paper/2105.12441/) (2021)
- [DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations](https://mlsanity.com/paper/1510.02927/) (2015)
- [TranSalNet: Towards perceptually relevant visual saliency prediction](https://mlsanity.com/paper/2110.03593/) (2021)
- [Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention](https://mlsanity.com/paper/2303.15274/) (2023)
- [PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks](https://mlsanity.com/paper/1809.00567/) (2018)
- [Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers](https://mlsanity.com/paper/2303.09383/) (2023)
- [End-to-End Saliency Mapping via Probability Distribution Prediction](https://mlsanity.com/paper/1804.01793/) (2018)
- [GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths](https://mlsanity.com/paper/2408.02788/) (2024)
- [ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts](https://mlsanity.com/paper/2310.15587/) (2023)
- [Beyond Average: Individualized Visual Scanpath Prediction](https://mlsanity.com/paper/2404.12235/) (2024)
- [SUM: Saliency Unification through Mamba for Visual Attention Modeling](https://mlsanity.com/paper/2406.17815/) (2024)
- [EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning](https://mlsanity.com/paper/2404.10163/) (2024)
- [Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction](https://mlsanity.com/paper/2507.23021/) (2025)
- [DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images](https://mlsanity.com/paper/2509.16767/) (2025)
- [Variational Flow Maps: Make Some Noise for One-Step Conditional Generation](https://mlsanity.com/paper/2603.07276/) (2026)
- [TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes](https://mlsanity.com/paper/2410.23409/) (2024)

## Abstract (arXiv)

We study the problem of human gaze modeling, which aims to generate the gaze patterns a viewer produces while observing a visual stimulus. Gaze is primarily captured through two modalities: continuous eye-tracking trajectories, which describe fine-grained motion dynamics, and discrete scanpaths, which describe high-level fixation structure. Because gaze varies substantially across viewers and trials, we treat this variability as a defining property rather than noise and model gaze as a stochastic generative process. Existing generative gaze models supervise on only one of these two representations in isolation. We hypothesize that trajectories and scanpaths describe gaze at complementary scales and are jointly informative during training, and test this hypothesis through ST-DiffEye, a joint trajectory-scanpath diffusion framework that couples both modalities by concatenating them as an additional raw input channel, requiring no architectural overhead beyond an input and output channel expansion. We further introduce a principled evaluation framework based on the Continuous Ranked Probability Score (CRPS), which generalizes any existing sequence similarity metric into a proper scoring rule that jointly assesses the accuracy and diversity of generated gaze. Experiments on task-driven visual search, covering both target-present and target-absent scenarios, and on free-viewing benchmarks demonstrate state-of-the-art performance. These results, along with detailed ablations, confirm the benefit of joint modeling and the value of distribution-aware evaluation in capturing the intrinsic variability of human gaze. Project webpage: https://st-diffeye.github.io/