Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Establishment of epidemiological cutoff values against <i>Fonsecaea monophora</i>, an agent of chromoblastomycosis and cerebral phaeohyphomycosis.

Journal of clinical microbiology·2026
Same author

Accelerating responsibly: From novelty to necessity in visual assistive technology.

Assistive technology : the official journal of RESNA·2026
Same author

Macromolecular Organization in Lentinula edodes: Integrating Co-Occurring Bioactives for Structure-Function Relationships Across Gut Microbiota and Host Metabolism.

Comprehensive reviews in food science and food safety·2026
Same author

Unusual Infections following Haploidentical Hematopoietic Stem cell Transplant in a Case with severe Aplastic Anaemia'.

Blood cell therapy·2026
Same author

Predominance of Fonsecaea nubica in Chromoblastomycosis: A Single-Centre Study from Southern India.

Mycopathologia·2026
Same author

Breaking the habit: Evidence-based approaches to smoking cessation.

Bioinformation·2026

Related Experiment Video

Updated: Nov 9, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.2K

Subject Guided Eye Image Synthesis with Application to Gaze Redirection.

Harsimran Kaur1, Roberto Manduchi1

  • 1University of California, Santa Cruz.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision
|April 14, 2021
PubMed
Summary

We developed a novel method to generate realistic eye images from segmentation masks, controlling for style attributes like skin and iris color. This technique enhances data augmentation and improves gaze redirection without needing real, annotated images.

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

656
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.3K

Related Experiment Videos

Last Updated: Nov 9, 2025

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.2K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

656
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.3K

Area of Science:

  • Computer Vision
  • Image Synthesis
  • Biometric Analysis

Background:

  • Current methods for synthetic eye image generation lack control over specific visual attributes.
  • Data augmentation for eye-related tasks often requires extensive real-world, annotated datasets.
  • Existing gaze redirection techniques may necessitate real eye images with gaze annotations.

Purpose of the Study:

  • To introduce a novel Style-Based eye image generation method using segmentation masks.
  • To enable the synthesis of eye images with controllable attributes (skin color, iris color, identity).
  • To apply the method for improved data augmentation and gaze redirection.

Main Methods:

  • A novel Style-Based Generative Adversarial Network (GAN) approach is proposed.
  • The method synthesizes eye images from segmentation masks, incorporating style from a reference image.
  • The approach is validated on data augmentation for tasks like gaze estimation and eye segmentation, and for gaze redirection.

Main Results:

  • The proposed method successfully generates realistic eye images with specified style attributes from segmentation masks.
  • Demonstrated effectiveness in data augmentation, producing diverse eye images for training downstream models.
  • Achieved state-of-the-art results in gaze redirection using only synthetic gaze labels, outperforming previous methods.

Conclusions:

  • The Style-Based eye image generation method offers precise control over synthesized image attributes.
  • This approach significantly enhances data augmentation capabilities for various eye-related computer vision tasks.
  • The method enables effective gaze redirection without reliance on real, gaze-annotated eye images.