AI Paper Atlas

Research map / Image generation / Editing and style transfer

Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Yisol Choi, Sangkyung Kwak, Kyungmin Lee, Hyungwon Choi, Jinwoo Shin

ECCV 2024 · Image generation › Editing and style transfer · approach: Virtual try-on · 171 citations (OpenAlex)

Read the paper

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 GarmentNet (parallel UNet feature encoder into self-attention) (ablation)IDM-VTON · VITON-HDLPIPS: 0.121 -> 0.102Improved
add GarmentNet (ablation)IDM-VTON · VITON-HDCLIP-I: 0.846 -> 0.883Improved
use detailed garment captions instead of naive captionsIDM-VTON · VITON-HD (qualitative)garment consistencyImproved
customize with a single person-garment pairIDM-VTON · In-the-WildLPIPS: 0.164 -> 0.150Improved
customize with a single person-garment pairStableVITON · In-the-WildLPIPS: 0.260 -> 0.259No clear effect
customize decoder (up-block) layers instead of LoRA (ablation)IDM-VTON customization · In-the-WildCLIP-I: 0.881 -> 0.909Improved
customize decoder layers instead of all UNet layers (ablation)IDM-VTON customization · In-the-WildCLIP-I: 0.891 -> 0.909Improved
any customization vs default (SSIM) (ablation)IDM-VTON · In-the-WildCLIP-I: 0.901 -> 0.891 (all UNet)No clear effect
IDM-VTON vs GAN-based GP-VTON on SSIMIDM-VTON · VITON-HDSSIM: 0.898 -> 0.870Hurt
train and test on DressCode, compare IDM-VTON with OOTDiffusionIDM-VTON · DressCode / VITON-HD cross-datasetFID: 57.87 -> 12.57Improved

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