PulseAugur
EN
LIVE 09:25:48

GazeDiT diffusion model generates precise eye-tracking training data

By PulseAugur Editorial · [1 sources] ·

Researchers have developed GazeDiT, a novel diffusion model designed to generate highly accurate synthetic images for eye-tracking training data. This model addresses the challenge of precise label control in diffusion models by internally constructing a spatial condition that grounds the global gaze label in local pupil and iris geometry. By leveraging a frozen SegFormer to extract geometric features and a physical eye renderer for diverse gaze-consistent geometries, GazeDiT significantly reduces gaze-label error compared to other diffusion baselines and improves the performance of downstream eye trackers. AI

IMPACT This research could lead to more accurate and efficient eye-tracking systems through improved synthetic data generation.

RANK_REASON The cluster contains an academic paper detailing a new model and its technical contributions. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

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

GazeDiT diffusion model generates precise eye-tracking training data

How we ranked this

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains an academic paper detailing a new model and its technical contributions. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Dongze Wu, David Colmenares, Fengting Yang, Jogendra Nath Kundu, Yao Xie, Ali Behrooz, Conny Lu ·

    GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning

    arXiv:2609.17814v1 Announce Type: new Abstract: Diffusion models are increasingly used to generate synthetic training data, but precise label control remains difficult when the conditioning signal is low-dimensional and coarse. Text-conditioned images are judged by broad prompt c…

RELATED ENTITIES

RELATED TOPICS