Research map / Image generation / Text-to-image diffusion
Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
Kihyun Na, Jinyoung Choi, Injung Kim
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 |
|---|---|---|---|
| switch CatVTON from attention-only to full fine-tuning (ablation) | CatVTON · VITON-HD 512x384 | Paired FID: 5.425 -> 5.250 | No clear effect |
| add Garment-Free Guidance (garment-free unconditional branch) (ablation) | CatVTON full FT · VITON-HD 512x384 | Paired FID: 5.250 -> 4.538 | Improved |
| add Garment-Free Guidance (ablation) | CatVTON full FT · VITON-HD 512x384 | Paired KID: 0.402 -> 0.074 | Improved |
| add Decoupled Loss (person-region loss only) (ablation) | CatVTON full FT + GFG · VITON-HD 512x384 | Paired FID: 4.538 -> 4.517 | Improved |
| add Clean Latent Anchoring at inference (ablation) | CatVTON full FT + GFG + DL · VITON-HD 512x384 | Paired FID: 4.517 -> 4.438 | Improved |
| add Clean Latent Anchoring at inference (ablation) | CatVTON full FT + GFG + DL · VITON-HD 512x384 | Paired KID: 0.068 -> 0.010 | Improved |
| add Decoupled Loss to GFG+CLA (ablation) | DeCo-VTON · VITON-HD 512x384 | Unpaired FID: 8.308 -> 8.266 | Improved |
| add Decoupled Loss to GFG+CLA (ablation) | DeCo-VTON · VITON-HD 512x384 | Paired KID: 0.004 -> 0.010 | Hurt |
| add Decoupled Loss to GFG+CLA (ablation) | DeCo-VTON · VITON-HD 1024x768 | Unpaired FID: 8.988 -> 8.675 | Improved |
| add Decoupled Loss to GFG+CLA (ablation) | DeCo-VTON · VITON-HD 1024x768 | Paired FID: 4.919 -> 4.741 | Improved |
| use garment-free guidance and anchoring so guidance scale can be raised (ablation) | DeCo-VTON vs CatVTON · VITON-HD guidance scale sweep | FID | Improved |
| full fine-tuning instead of attention-only in Voost DiT (reported by Voost) | Voost · VITON-HD 1024x768 | FID: 5.269 -> 6.351 | Hurt |
Closest papers by meaning
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.91)
- OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025 · similarity 0.90)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.90)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.89)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.89)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.89)
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.
