CVPR 2026 Highlight

Vanast
Virtual Try-On with Human Image Animation
via Synthetic Triplet Supervision

Hyunsoo Cha Wonjung Woo Byungjun Kim Hanbyul Joo

Seoul National University

Paper arXiv Code (Coming Soon)

TL;DR — Given a human image and one or more garment images, our method generates virtual try-on with human image animation conditioned on a pose video while preserving identity.

Demonstrations

Results

All result videos are complete zero-shot inference results not included in the training set, without any additional training or optimization.

Upper-body Clothing Transfer

Lower-body Clothing Transfer

Dress Transfer

Hat Transfer

Extended Capabilities

Applications

All result videos are complete zero-shot inferences, showing the transfer of multiple attributes simultaneously or interpolation between attributes.

Multiple Garment Transfer

In-the-wild Garment Transfer

Garment Interpolation

Citation

BibTeX

@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}
}