Research map / Video / Video generation
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo
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 |
|---|---|---|---|
| use Dual Module (separate HAM and GTM) instead of a single module (ablation) | Vanast · Ablation (Table 3) | FID: 108.84 -> 104.59 | Improved |
| use Dual Module instead of Backbone-LoRA (ablation) | Vanast · Ablation (Table 3) | FID: 120.97 -> 104.59 | Improved |
| train with synthesized human image in alternate outfit (ablation) | Vanast · Ablation (Table 3) | FID: 110.76 -> 104.59 | Improved |
| train with synthesized human image in alternate outfit (ablation) | Vanast · Ablation (Table 3) | VFID I3D: 38.89 -> 35.60 | Improved |
| unified single-stage vs best two-stage try-on+animation | Vanast · Internet dataset | FID: 111.08 -> 91.05 | Improved |
| unified single-stage vs best two-stage try-on+animation | Vanast · Internet dataset | SSIM: 0.7779 -> 0.7550 | Hurt |
| unified single-stage vs best subject-to-image+animation | Vanast · ViViD dataset | FID: 140.26 -> 105.89 | Improved |
| unified single-stage vs VACE 1-stage | Vanast · Internet dataset | FID: 115.40 -> 91.05 | Improved |
Closest papers by meaning
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.89)
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization (NeurIPS 2026 · similarity 0.89)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.88)
- Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling (CVPR 2025 · similarity 0.88)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · 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.
