Research map / Image generation / Editing and style transfer
GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use local flows in place of a global flow (ablation) | LFGP warping module · VITON-HD | mIoU: 0.8412 -> 0.8784 | Helped |
| use local flows in place of a global flow (ablation) | LFGP warping module · VITON-HD | SSIM: 0.9016 -> 0.9039 | Helped |
| add standard gradient truncation (ablation) | LFGP with local flows · VITON-HD | R_diff: 0.3003 -> 0.2409 | Helped |
| replace standard gradient truncation with dynamic gradient truncation (ablation) | LFGP with local flows · VITON-HD | R_diff: 0.2409 -> 0.1655 | Helped |
| use dynamic gradient truncation instead of standard gradient truncation (ablation) | LFGP with local flows · VITON-HD | LPIPS: 0.0900 -> 0.0884 | Helped |
| use global garment parsing to assemble the locally warped parts (ablation) | LFGP warping module · VITON-HD | overlap artifacts | Helped |
| use GP-VTON rather than the strongest listed baseline | VITON-HD try-on · VITON-HD | HE: 16.3% -> 50.9% | Helped |
| use GP-VTON rather than the strongest listed baseline | DressCode-Upper try-on · DressCode-Upper | FID: 12.61 -> 11.98 | Helped |
| use GP-VTON rather than the strongest listed baseline | DressCode-Lower try-on · DressCode-Lower | FID: 16.05 -> 16.07 | No clear effect |
| use GP-VTON rather than the strongest listed baseline | DressCode-Dresses try-on · DressCode-Dresses | SSIM: 0.8876 -> 0.8866 | Hurt |
| use GP-VTON rather than the strongest listed baseline | DressCode-Dresses try-on · DressCode-Dresses | FID: 11.80 -> 12.26 | Hurt |
| use GP-VTON rather than the strongest listed baseline | DressCode-Dresses try-on · DressCode-Dresses | HE: 19.3% -> 55.0% | Helped |
Closest papers by meaning
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.89)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.89)
- Towards Squeezing-Averse Virtual Try-On via Sequential Deformation (AAAI 2024 · similarity 0.89)
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.89)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.89)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.88)
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.