Research map / Image generation / Editing and style transfer
Virtual Try-On: Real-Time Interactive Hybrid Network with High-Fidelity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a hybrid interactive virtual try-on system combining OpenPose keypoint extraction, a geometric appearance flow alteration, and a triangulation-mesh wrapping module for real-time, multi-category clothing try-on.
Problem
Image-based virtual try-on faces artifacts, limited clothing categories (mostly upper-body), noisy results, and high computational cost, which hinder real-world deployment.
Approach
Replaces purely generative synthesis with a hybrid pipeline of rule-based geometric operations (posture angle criteria, keypoint-based appearance flow alteration, and structured triangulation mesh wrapping) so that clothes keep their shape and extra space beyond body contours is generated for garments like flared skirts.
Key results
- No quantitative results are reported; the paper only describes a demonstration of the system with uploaded user images and varied clothing categories.
Limitations
- No quantitative evaluation or comparison against baselines is provided.
- Handles only relatively simple human poses; complex poses are deferred to future work.
- Relies on hand-crafted geometric formulas whose generality across garments is not demonstrated.
Experimental setup
Baselines: VITON ACGPN
Builds on: OpenPose VITON ACGPN
Closest papers by meaning
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.88)
- AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario (NeurIPS 2024 · similarity 0.88)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.88)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.87)
- OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.