Research map / Image generation / Editing and style transfer
Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks
Hailong Guo, Bohan Zeng, Yiren Song, Wentao Zhang, Jiaming Liu, Chuang Zhang
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 clean latent image conditions (not noised) to the input (ablation) | Any2AnyTryon · Ablation | LPIPS: 0.3141 -> 0.2590 | Improved |
| add clean latent image conditions (not noised) to the input (ablation) | Any2AnyTryon · Ablation | SSIM: 0.6892 -> 0.7373 | Improved |
| add clean latent image conditions (not noised) to the input (ablation) | Any2AnyTryon · Ablation | CLIP-FID: 9.648 -> 9.293 | Improved |
| add clean latent image conditions (not noised) to the input (ablation) | Any2AnyTryon · Ablation | KID: 6.403 -> 5.407 | Improved |
| add adaptive position embedding (ablation) | Any2AnyTryon · Ablation | LPIPS: 0.3080 -> 0.2590 | Improved |
| add adaptive position embedding (ablation) | Any2AnyTryon · Ablation | SSIM: 0.7088 -> 0.7373 | Improved |
| add adaptive position embedding (ablation) | Any2AnyTryon · Ablation | CLIP-FID: 9.434 -> 9.293 | Improved |
| add adaptive position embedding (ablation) | Any2AnyTryon · Ablation | KID: 5.658 -> 5.407 | Improved |
| use Any2AnyTryon instead of TryOffDiff for garment reconstruction | TryOffDiff · VITON-HD garment reconstruction | FID: 20.346 -> 13.367 | Improved |
| use Any2AnyTryon instead of TryOffDiff for garment reconstruction | TryOffDiff · VITON-HD garment reconstruction | MS-SSIM: 0.712 -> 0.710 | No clear effect |
| use Any2AnyTryon instead of StableGarment for model-free try-on | StableGarment · VITON-HD model-free try-on | CLIP-I: 0.650 -> 0.789 | Improved |
| use Any2AnyTryon instead of CatVTON for mask-free try-on | CatVTON · VITON-HD try-on (paired) | FID: 5.482 -> 6.934 | Hurt |
Later papers that compared with this method
6 later accepted papers report Any2AnyTryon as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- PG-VTON: Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment (CVPR 2026 · better on 7 of 8 shared results)
- Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals (ICLR 2026 · better on 5 of 5 shared results)
- Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off (ECCV 2026 · better on 4 of 5 shared results)
- PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On (CVPR 2026 · better on 3 of 4 shared results)
- OrthoTailor: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation (ECCV 2026 · better on 4 of 4 shared results)
- Correpondence Alignment For Improved Virtual Try-On (NeurIPS 2026 · better on 0 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
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.93)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.92)
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.91)
- AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario (NeurIPS 2024 · similarity 0.91)
- OmniTry: Virtual Try-On Anything without Masks (NeurIPS 2025 · similarity 0.90)
- Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling (CVPR 2025 · similarity 0.90)
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.
