Research map / Image generation / Editing and style transfer
PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On
Haohua Chen, Tianze Zhou, Wei Zhu, Runqi Wang, Yandong Guan, Dejia Song, Yibo Chen, Xu Tang, Yao Hu, Lu Sheng, Zhiyong Wu
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 3D-RoPE group identifiers (ablation) | PROMO · DressCode paired | FID: 6.7293 -> 3.3103 | Improved |
| add style prompt (ablation) | PROMO · DressCode paired | FID: 3.7178 -> 3.3103 | Improved |
| add parsing area loss (ablation) | PROMO · DressCode paired | FID: 3.2847 vs 3.3103 | No clear effect |
| add parsing area loss (ablation) | PROMO · in-the-wild | qualitative fidelity | Improved |
| add temporal self-reference (ablation) | PROMO · DressCode | inference time (s): 22.2378 -> 9.1775 | Improved |
| add temporal self-reference (ablation) | PROMO · DressCode paired | FID: 3.3102 vs 3.3103 | No clear effect |
| add temporal self-reference (ablation) | PROMO · DressCode paired | KID: 0.7975 -> 0.4902 | Improved |
| add spatial token merging (ablation) | PROMO · DressCode | inference time (s): 11.1030 -> 9.1775 | Improved |
| add spatial token merging (ablation) | PROMO · DressCode paired | FID: 3.4878 vs 3.3103 | No clear effect |
| use PROMO instead of general image editing models | PROMO · DressCode paired | FID: 10.7050 (Nanobanana) -> 8.9268 | Improved |
| use PROMO instead of PromptDresser | PROMO · VITON-HD paired | LPIPS: 0.1163 vs 0.1111 | No clear effect |
| use PROMO instead of Any2AnyTryon | PROMO · DressCode paired | FID: 3.0828 vs 3.3103 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- OOTDiffusion — OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025) · better on 4 of 4 shared results
- Any2AnyTryon — Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks (ICCV 2025) · better on 3 of 4 shared results
- PromptDresser — PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask (ICCV 2025) · better on 2 of 2 shared results
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
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.87)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.87)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.87)
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.86)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · 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.
