AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask

Jeongho Kim, Hoiyeong Jin, Sunghyun Park, Jaegul Choo

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 16 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 prompt-aware mask generation (PMG) at inference (ablation)PromptDresser · VITON-HDFID: 8.98 -> 8.54Improved
add PMG at inference (ablation)PromptDresser · VITON-HDSSIM: 0.8411 -> 0.8686Improved
add PMG at inference (ablation)PromptDresser · VITON-HDLPIPS: 0.1485 -> 0.1119Improved
use structured attribute captions instead of holistic description (ablation)PromptDresser · VITON-HDFID: 9.21 -> 8.54Improved
use structured attribute captions instead of holistic description (ablation)PromptDresser · VITON-HDKID: 1.18 -> 0.67Improved
use GPT-4o captions instead of LLaVA (ablation)PromptDresser · VITON-HDFID: 8.85 -> 8.54Improved
add generative text prompt to IDM-VTONIDM-VTON · VITON-HDFID: 9.20 -> 9.15Improved
add generative text prompt to IDM-VTONIDM-VTON · VITON-HDLPIPS: 0.1023 -> 0.1025No clear effect
add DensePose channels (13-channel input)PromptDresser · VITON-HDLPIPS: 0.1119 -> 0.0967Improved
add DensePose channelsPromptDresser · VITON-HDKID: 0.67 -> 1.16Hurt
add DensePose channelsPromptDresser · Text alignment 'tight fit'Accuracy: 66.98% -> 44.09%Hurt
lower sigma from 0.8 to 0.3 for PMG early stopping (ablation)PromptDresser · VITON-HDKID: 0.68 -> 0.65No clear effect

Later papers that compared with this method

2 later accepted papers report PromptDresser as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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