Research map / Image generation / Editing and style transfer
RefTon: Reference person shot assist virtual Try-on
Liuzhuozheng Li, Yue Gong, Shanyuan Liu, Zanyi Wang, Dengyang Jiang, Leibucha Wu, Bo Cheng, Yuhang Ma, Dawei Leng, Yuhui Yin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add reference images at inference and training (ablation) | RefTON · VITON-HD paired | FID: 5.45 -> 4.69 | Improved |
| add reference images (ablation) | RefTON · VITON-HD unpaired | FID: 8.58 -> 8.43 | Improved |
| add reference images (ablation) | RefTON · DressCode paired | FID: 3.48 -> 2.94 | Improved |
| add reference images to mask-free model (ablation) | RefTON/MF · VITON-HD paired | FID: 5.98 -> 5.11 | Improved |
| add reference images to mask-free model (ablation) | RefTON/MF · DressCode unpaired | FID: 5.00 -> 5.02 | No clear effect |
| go from mask-based to mask-free input (ablation) | RefTON · VITON-HD paired | FID: 5.45 -> 5.98 | Hurt |
| go from mask-based to mask-free input (ablation) | RefTON · VITON-HD unpaired | FID: 8.58 -> 8.40 | Improved |
| use rescaled position index instead of original Flux-Kontext index (ablation) | RefTON · VITON-HD, 0.5 scale | FID: 5.29 -> 5.09 | Improved |
| use rescaled position index (ablation) | RefTON · VITON-HD, 0.25 scale mask-free | FID: 5.35 -> 5.37 | No clear effect |
| train on mixed VFR dataset | RefTON · VITON-HD paired | FID: 11.22 -> 6.23 | Improved |
| use P2P RefTON vs OmniVTON on StreetTryOn | RefTON · StreetTryOn P-to-St | FID: 33.450 -> 25.429 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- OmniVTON — OmniVTON: Training-Free Universal Virtual Try-On (ICCV 2025) · better on 2 of 2 shared results
- OOTDiffusion — OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter (AAAI 2025 · similarity 0.88)
- Correpondence Alignment For Improved Virtual Try-On (NeurIPS 2026 · similarity 0.88)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.87)
- Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling (CVPR 2025 · similarity 0.87)
- HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion (CVPR 2024 · similarity 0.86)
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.86)
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.
