# Infinite Gaze Generation for Videos with Autoregressive Diffusion

arXiv: https://arxiv.org/abs/2603.24938 · HTML: https://mlsanity.com/paper/2603.24938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Video World Models with Long-term Spatial Memory](https://mlsanity.com/paper/2506.05284/) (2025)
- [Epona: Autoregressive Diffusion World Model for Autonomous Driving](https://mlsanity.com/paper/2506.24113/) (2025)
- [Unified Image and Video Saliency Modeling](https://mlsanity.com/paper/2003.05477/) (2020)
- [Revisiting Video Saliency: A Large-scale Benchmark and a New Model](https://mlsanity.com/paper/1801.07424/) (2018)
- [Long-Context State-Space Video World Models](https://mlsanity.com/paper/2505.20171/) (2025)
- [DiffuserLite: Towards Real-time Diffusion Planning](https://mlsanity.com/paper/2401.15443/) (2024)
- [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)
- [ScanGAN360: A Generative Model of Realistic Scanpaths for 360circ Images](https://mlsanity.com/paper/2103.13922/) (2021)
- [Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers](https://mlsanity.com/paper/2303.09383/) (2023)
- [OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction](https://mlsanity.com/paper/2407.13335/) (2024)
- [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)
- [Fr'echet Distance for Curves, Revisited](https://mlsanity.com/paper/1504.07685/) (2015)
- [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)
- [Foveated Instance Segmentation](https://mlsanity.com/paper/2503.21854/) (2025)

## Abstract (arXiv)

Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, both abstractions often collapse the fine-grained temporal dynamics of raw gaze. Furthermore, existing models are typically constrained to short-term windows (≈ 3-5s), failing to capture the long-range behavioral dependencies inherent in real-world content. We present a generative framework for infinite-horizon raw gaze prediction in videos of arbitrary length. By leveraging an autoregressive diffusion model, we synthesize gaze trajectories characterized by continuous spatial coordinates and high-resolution timestamps. Our model is conditioned on a saliency-aware visual latent space. Quantitative and qualitative evaluations demonstrate that our approach significantly outperforms existing approaches in long-range spatio-temporal accuracy and trajectory realism.