New Diffusion Model Generates Human Gaze Patterns by Integrating Trajectories and Scanpaths

Researchers have developed ST-DiffEye, a novel diffusion framework for generating human gaze patterns. This model uniquely integrates both continuous eye-tracking trajectories and discrete scanpaths, treating gaze variability as a core feature rather than noise. The framework utilizes a joint modeling approach by concatenating these modalities as an input channel, requiring minimal architectural changes. An accompanying evaluation framework based on the Continuous Ranked Probability Score (CRPS) is also introduced to assess both accuracy and diversity of generated gaze. AI

IMPACT This research advances generative models for human behavior analysis, potentially impacting fields like HCI and user experience research.

RANK_REASON The cluster contains a research paper detailing a new AI model and evaluation framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• Brian Nlong Zhao
• CatalyzeX Code Finder for Papers
• Continuous Ranked Probability Score
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• ScienceCast
• ST-DiffEye

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →