Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917456172285952 |
|---|---|
| author | Cha, Hyunsoo Woo, Wonjung Kim, Byungjun Joo, Hanbyul |
| author_facet | Cha, Hyunsoo Woo, Wonjung Kim, Byungjun Joo, Hanbyul |
| contents | We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04934 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision Cha, Hyunsoo Woo, Wonjung Kim, Byungjun Joo, Hanbyul Computer Vision and Pattern Recognition We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types. |
| title | Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.04934 |