AI Paper Atlas

Research map / Image generation / Editing and style transfer

Learning Implicit Features with Flow-Infused Transformations for Realistic Virtual Try-On

Delong Zhang, Qiwei Huang, Yang Sun, Yuanliu Liu, Wei-Shi Zheng, Pengfei Xiong, Wei Zhang

ICCV 2025 · Image generation › Editing and style transfer · approach: Virtual try-on · 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
add Flow Guider (ablation)FIA-VTON · VITON-HDFID paired: 5.438 -> 4.686Improved
add Flow Guider (ablation)FIA-VTON · VITON-HDFID unpaired: 8.530 -> 7.914Improved
add Spatial Guider (ablation)FIA-VTON · VITON-HDFID unpaired: 8.645 -> 7.914Improved
add Spatial Guider (ablation)FIA-VTON · VITON-HDSSIM: 0.888 -> 0.913Improved
add Spatial Guider (ablation)FIA-VTON · VITON-HDPSNR: 24.330 -> 27.827Improved
use FashionCLIP instead of OpenCLIP as Spatial Guider (ablation)FIA-VTON · VITON-HDFID unpaired: 8.032 -> 7.914Improved
use FashionCLIP instead of OpenCLIP as Spatial Guider (ablation)FIA-VTON · VITON-HDSSIM: 0.914 -> 0.913No clear effect
use flow-infused attention instead of concatenated input (ablation)FIA-VTON · VITON-HDFID paired: 4.950 -> 4.686Improved
use flow-infused attention instead of plain cross-attention (ablation)FIA-VTON · VITON-HDFID paired: 5.28 -> 4.686Improved
use flow-infused attention instead of plain cross-attention (ablation)FIA-VTON · VITON-HDSSIM: 0.904 -> 0.913Improved
use bilinear instead of cubic downsampling for evaluationFIA-VTON · VITON-HDFID paired: 5.124 -> 4.686Mixed
FIA-VTON vs best warp-based D4-VTONFIA-VTON · DressCode-LowerFID unpaired: 14.86 -> 10.58Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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