Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Screening frost-tolerant kale (Brassica oleracea L. var. acephala) genotypes through cold-responsive metabolic changes in open field conditions.

Journal of plant physiology·2026

Same author

Establishment and phenotypic characterization of genetically diverse core collections of Lupinus albus.

BMC plant biology·2025

Same author

Autoimmune gastritis detection from preprocessed endoscopy images using deep transfer learning and moth flame optimization.

Scientific reports·2025

Same author

Genomic insights into genetic diversity and seed coat color change in common bean composite populations.

Frontiers in plant science·2025

Same author

Dissecting the Genetic Architecture of Morphological Traits in Sunflower (<i>Helianthus annuus</i> L.).

Genes·2024

Same author

Agro-Morphological and Molecular Characterization Reveal Deep Insights in Promising Genetic Diversity and Marker-Trait Associations in <i>Fagopyrum esculentum</i> and <i>Fagopyrum tataricum</i>.

Plants (Basel, Switzerland)·2023

Same journal

Human-like scene graph generation and evaluation.

Multimedia tools and applications·2026

Same journal

LuGSAM: a novel framework for integrating text prompts to Segment Anything Model (SAM) for segmentation tasks of ICU chest x-rays.

Multimedia tools and applications·2025

Same journal

Brain magnetic resonance image (MRI) segmentation using multimodal optimization.

Multimedia tools and applications·2025

Same journal

Enhancing road safety: In-vehicle sensor analysis of cognitive impairment in older drivers.

Multimedia tools and applications·2025

Same journal

Decision support for augmented reality-based assistance systems deployment in industrial settings.

Multimedia tools and applications·2025

Same journal

Real-time violence detection and localization through subgroup analysis.

Multimedia tools and applications·2025

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 20, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Dress-up: deep neural framework for image-based human appearance transfer.

Hajer Ghodhbani¹, Mohamed Neji^1,2, Abdulrahman M Qahtani³

¹REsearch Groups in Intelligent Machines (REGIM Lab), University of Sfax, National Engineering School of Sfax (ENIS), BP 1173, Sfax, 3038 Tunisia.

Multimedia Tools and Applications

|November 21, 2022

Summary

This summary is machine-generated.

We developed Dress-up, a flexible AI system for virtual try-on, enabling realistic clothing transfer across images without 3D models. This technology enhances online shopping by improving purchase decisions and user experience.

Keywords:

Artificial intelligence Garment interchange Outfit generation Semantic segmentation Virtual try-on

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Aug 20, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Fashion Technology

Background:

The fashion industry is undergoing a transformation driven by Artificial Intelligence (AI).
Virtual try-on technologies offer significant opportunities to enhance the online shopping experience and stimulate consumer purchasing intentions.
Existing methods face challenges in accurately transferring clothing appearance across diverse source and target images, especially with significant variations.

Purpose of the Study:

To introduce a novel flexible person generation framework, Dress-up, for 2D virtual try-on applications.
To enable high-quality human appearance transfer across images, preserving garment details and structural coherence.
To overcome limitations in existing virtual try-on systems, particularly concerning image divergence and lack of direct supervision.

Main Methods:

An end-to-end generation pipeline comprising three modules based on image-to-image translation.
A pre-processing module using semantic segmentation to encode body pose and target clothing.
A conditional adversarial network generating target segmentation, feeding alignment and translation networks for final output.

Main Results:

The Dress-up system successfully reconstructs garments on different human poses and appearances from semantic maps and 2D images, without employing 3D modeling.
Achieved significant improvements over state-of-the-art methods on the DeepFashion dataset in terms of output quality.
Demonstrated robustness and effectiveness in handling a wide range of editing functions without direct supervision.

Conclusions:

Dress-up provides a high-quality, flexible solution for 2D virtual try-on, advancing intelligent fashion applications.
The proposed method outperforms existing approaches in realism and detail preservation for virtual try-on.
This framework offers a robust and effective approach to human appearance transfer for virtual try-on, enhancing online fashion retail.