Research map / Image generation / Text-to-image diffusion
TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On
Jiazheng Xing, Chao Xu, Yijie Qian, Yang Liu, Guang Dai, Baigui Sun, Yong Liu, Jingdong Wang
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 fine-tuning of attention layers to frozen model (ablation) | Paint-by-Example · VITON-HD | FID_u: 23.48 -> 11.00 | Improved |
| add style adaptation (ablation) | TryOn-Adapter · VITON-HD | FID_u: 11.00 -> 8.89 | Improved |
| add texture adaptation (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.89 -> 8.73 | Improved |
| add segmentation adaptation (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.73 -> 8.63 | Improved |
| add style adapter (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.69 -> 8.62 | Improved |
| add position attention module (PAM) (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.65 -> 8.62 | Improved |
| add ELBM to SD autoencoder (ablation) | Stable Diffusion VAE · Reconstruction | LPIPS: 0.024 -> 0.020 | Improved |
| add ELBM (ablation) | TryOn-Adapter · Try-On (paired) | SSIM: 0.867 -> 0.897 | Improved |
| use RePaint for half of denoising steps (ablation) | TryOn-Adapter · VITON-HD | LPIPS: 0.071 -> 0.069 | Improved |
| use RePaint for all steps instead of half (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.62 -> 8.99 | Hurt |
| use RePaint for 3/4 steps instead of half (ablation) | TryOn-Adapter · VITON-HD | FID_u: 8.62 -> 8.67 | Hurt |
| full fine-tuning instead of PEFT (ablation) | TryOn-Adapter · VITON-HD | LPIPS: 0.069 -> 0.068 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GP-VTON — GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning (CVPR 2023) · better on 3 of 3 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
- Time-Efficient and Identity-Consistent Virtual Try-On Using A Variant of Altered Diffusion Models (ECCV 2024 · similarity 0.93)
- All Parts Matter: A Unified Mask-Free Virtual Try-On Framework (ICCV 2025 · similarity 0.91)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.90)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.90)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.90)
- 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.
