- [2026.04] Paper accepted to CVPR 2026 as a Highlight!
- [2026.04] arXiv preprint and project page are released.
- Release project page
- Release arXiv paper
- Release inference code & pretrained weights (May 2026)
- Release Gradio demo
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.
If you find our work useful, please consider citing:
@inproceedings{cha2026vanast,
title = {Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision},
author = {Cha, Hyunsoo and Woo, Wonjung and Kim, Byungjun and Joo, Hanbyul},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026}
}This work was conducted at SNU VCLab.
This project is licensed under CC BY 4.0.