Research map / Image generation / Editing and style transfer
FitControler: Toward Fit-Aware Virtual Try-On
Lu Yang, Yicheng Liu, Letian Zhou, Yanan Li, Xiang Bai, Hao Lu
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 FitControler | FitDiT · Fit4Men short-sleeve (paired) | FID: 17.40 -> 12.51 | Improved |
| add FitControler | FitDiT · Fit4Men short-sleeve (paired) | Hu: 0.65 -> 0.38 | Improved |
| add FitControler | Leffa · Fit4Men short-sleeve (paired) | Hd: 9.18 -> 7.05 | Improved |
| add FitControler | StableVITON · Fit4Men short-sleeve (paired) | FID: 16.93 -> 14.39 | Improved |
| add FitControler | IDM-VTON · Fit4Men trousers (paired) | Hu: 1.03 -> 0.81 | Improved |
| add FitControler | CatVTON-FLUX · Fit4Men trousers (paired) | Hd: 13.38 -> 9.49 | Improved |
| add FitControler | FitDiT · Fit4Men regular-fit subset (paired) | FID: 24.97 -> 18.17 | Improved |
| use multi-scale fit injector instead of ControlNet (ablation) | FitControler (Leffa) · Fit4Men short-sleeve (paired) | FID: 13.14 -> 12.13 | Improved |
| use multi-scale fit injector instead of ControlNet (ablation) | FitControler (Leffa) · Fit4Men short-sleeve (paired) | trainable params: 361M -> 97M | Improved |
| train on 1000 samples instead of full 3959 (ablation) | FitControler (Leffa) · Fit4Men short-sleeve (unpaired) | FID: 17.50 vs 17.80 (full) | No clear effect |
| add FitControler instead of backbone finetuning (ablation) | Leffa · Fit4Men short-sleeve (unpaired) | Hd: 12.67 -> 7.65 | Improved |
| backbone finetuning on Fit4Men without FitControler (ablation) | FitDiT · Fit4Men short-sleeve (unpaired) | Hu: 0.80 -> 0.81 | No clear effect |
Closest papers by meaning
- Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks (ICCV 2025 · similarity 0.92)
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.88)
- AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario (NeurIPS 2024 · similarity 0.88)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.88)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · 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.
