AI Paper Atlas

Research map / Image generation / Editing and style transfer

PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On

Haohua Chen, Tianze Zhou, Wei Zhu, Runqi Wang, Yandong Guan, Dejia Song, Yibo Chen, Xu Tang, Yao Hu, Lu Sheng, Zhiyong Wu

CVPR 2026 · 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 3D-RoPE group identifiers (ablation)PROMO · DressCode pairedFID: 6.7293 -> 3.3103Improved
add style prompt (ablation)PROMO · DressCode pairedFID: 3.7178 -> 3.3103Improved
add parsing area loss (ablation)PROMO · DressCode pairedFID: 3.2847 vs 3.3103No clear effect
add parsing area loss (ablation)PROMO · in-the-wildqualitative fidelityImproved
add temporal self-reference (ablation)PROMO · DressCodeinference time (s): 22.2378 -> 9.1775Improved
add temporal self-reference (ablation)PROMO · DressCode pairedFID: 3.3102 vs 3.3103No clear effect
add temporal self-reference (ablation)PROMO · DressCode pairedKID: 0.7975 -> 0.4902Improved
add spatial token merging (ablation)PROMO · DressCodeinference time (s): 11.1030 -> 9.1775Improved
add spatial token merging (ablation)PROMO · DressCode pairedFID: 3.4878 vs 3.3103No clear effect
use PROMO instead of general image editing modelsPROMO · DressCode pairedFID: 10.7050 (Nanobanana) -> 8.9268Improved
use PROMO instead of PromptDresserPROMO · VITON-HD pairedLPIPS: 0.1163 vs 0.1111No clear effect
use PROMO instead of Any2AnyTryonPROMO · DressCode pairedFID: 3.0828 vs 3.3103Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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