Paper Detail

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

Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo

arxiv Score 3.8

Published 2026-04-06 · First seen 2026-04-07

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{cha2026vanast,
  title = {Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision},
  author = {Hyunsoo Cha and Wonjung Woo and Byungjun Kim and Hanbyul Joo},
  year = {2026},
  abstract = {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},
  url = {https://arxiv.org/abs/2604.04934},
  keywords = {cs.CV, virtual try-on, pose-driven animation, garment transfer, video diffusion transformers, dual module architecture, triplet supervision, identity preservation, garment accuracy, pose adherence, code available, huggingface daily},
  eprint = {2604.04934},
  archiveprefix = {arXiv},
}

Metadata

{}