AI Paper Atlas

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

CVPR 2026 · Video › Video generation · approach: Diffusion-based human image animation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use Dual Module (separate HAM and GTM) instead of a single module (ablation)Vanast · Ablation (Table 3)FID: 108.84 -> 104.59Improved
use Dual Module instead of Backbone-LoRA (ablation)Vanast · Ablation (Table 3)FID: 120.97 -> 104.59Improved
train with synthesized human image in alternate outfit (ablation)Vanast · Ablation (Table 3)FID: 110.76 -> 104.59Improved
train with synthesized human image in alternate outfit (ablation)Vanast · Ablation (Table 3)VFID I3D: 38.89 -> 35.60Improved
unified single-stage vs best two-stage try-on+animationVanast · Internet datasetFID: 111.08 -> 91.05Improved
unified single-stage vs best two-stage try-on+animationVanast · Internet datasetSSIM: 0.7779 -> 0.7550Hurt
unified single-stage vs best subject-to-image+animationVanast · ViViD datasetFID: 140.26 -> 105.89Improved
unified single-stage vs VACE 1-stageVanast · Internet datasetFID: 115.40 -> 91.05Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy