# PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1809.00567 · HTML: https://mlsanity.com/paper/1809.00567/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2018.

## Built on by (most cited first, 30 of 32)

- [ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Images](https://mlsanity.com/paper/2103.13922/) (2021)
- [State-of-the-Art in Human Scanpath Prediction](https://mlsanity.com/paper/2102.12239/) (2021)
- [Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers](https://mlsanity.com/paper/2303.09383/) (2023)
- [ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery](https://mlsanity.com/paper/2112.08189/) (2021)
- [Synthesizing Human Gaze Feedback for Improved NLP Performance](https://mlsanity.com/paper/2302.05721/) (2023)
- [GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths](https://mlsanity.com/paper/2408.02788/) (2024)
- [Eye-tracked Virtual Reality: A Comprehensive Survey on Methods and Privacy Challenges](https://mlsanity.com/paper/2305.14080/) (2023)
- [Beyond Average: Individualized Visual Scanpath Prediction](https://mlsanity.com/paper/2404.12235/) (2024)
- [EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning](https://mlsanity.com/paper/2404.10163/) (2024)
- [SALYPATH: A Deep-Based Architecture for visual attention prediction](https://mlsanity.com/paper/2107.00559/) (2021)
- [Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention](https://mlsanity.com/paper/2204.09093/) (2022)
- [Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction](https://mlsanity.com/paper/2507.23021/) (2025)
- [A domain adaptive deep learning solution for scanpath prediction of paintings](https://mlsanity.com/paper/2209.11338/) (2022)
- [Scanpath Prediction on Information Visualisations](https://mlsanity.com/paper/2112.02340/) (2021)
- [Perceptual Quality Assessment of 360^circ Images Based on Generative Scanpath Representation](https://mlsanity.com/paper/2309.03472/) (2023)
- [Few-shot Personalized Scanpath Prediction](https://mlsanity.com/paper/2504.05499/) (2025)
- [DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images](https://mlsanity.com/paper/2509.16767/) (2025)
- [SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images](https://mlsanity.com/paper/2201.00096/) (2022)
- [Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shifts](https://mlsanity.com/paper/2207.04250/) (2022)
- [Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization](https://mlsanity.com/paper/2305.02536/) (2023)
- [TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes](https://mlsanity.com/paper/2410.23409/) (2024)
- [An Inter-observer consistent deep adversarial training for visual scanpath prediction](https://mlsanity.com/paper/2211.07336/) (2022)
- [Learning Saliency From Fixations](https://mlsanity.com/paper/2311.14073/) (2023)
- [Impact of Design Decisions in Scanpath Modeling](https://mlsanity.com/paper/2405.08981/) (2024)
- [A Simple and efficient deep Scanpath Prediction](https://mlsanity.com/paper/2112.04610/) (2021)
- [SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation](https://mlsanity.com/paper/2602.22049/) (2026)
- [Pathformer3D: A 3D Scanpath Transformer for 360deg Images](https://mlsanity.com/paper/2407.10563/) (2024)
- [Visual Attention Graph](https://mlsanity.com/paper/2503.08531/) (2025)
- [A Comparative Study of Scanpath Models in Graph-Based Visualization](https://mlsanity.com/paper/2503.24160/) (2025)
- [Infinite Gaze Generation for Videos with Autoregressive Diffusion](https://mlsanity.com/paper/2603.24938/) (2026)

## Abstract (arXiv)

We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples. A visual scanpath is defined as the sequence of fixation points over an image defined by a human observer with its gaze. PathGAN is composed of two parts, the generator and the discriminator. Both parts extract features from images using off-the-shelf networks, and train recurrent layers to generate or discriminate scanpaths accordingly. In scanpath prediction, the stochastic nature of the data makes it very difficult to generate realistic predictions using supervised learning strategies, but we adopt adversarial training as a suitable alternative. Our experiments prove how PathGAN improves the state of the art of visual scanpath prediction on the iSUN and Salient360! datasets. Source code and models are available at https://imatge-upc.github.io/pathgan/