AI Paper Atlas

Research map / Image generation / Editing and style transfer

Be Your Own Prada: Fashion Synthesis With Structural Coherence

Shizhan Zhu, Raquel Urtasun, Sanja Fidler, Dahua Lin, Chen Change Loy

ICCV 2017 · Image generation › Editing and style transfer · approach: Virtual try-on · 301 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 two-step shape-then-image generation instead of one-step GAN with 8x8x7 prior (ablation)One-Step-8-7 · DeepFashion attribute detection on synthesized imagesmAP (%): 72.4 -> 82.6Improved
use two-step shape-then-image generation instead of one-step GAN with merged 8x8x4 prior (ablation)One-Step-8-4 · DeepFashion attribute detection on synthesized imagesmAP (%): 73.3 -> 82.6Improved
add segmentation-guided compositional mapping (ablation)Non-Compositional two-stage GAN · DeepFashion attribute detection on synthesized imagesmAP (%): 74.7 -> 82.6Improved
add deep generative model over non-deep baselineNon-Deep · DeepFashion attribute detection on synthesized imagesmAP (%): 71.8 -> 82.6Improved
merge segmentation classes (8x8x4) instead of non-merged (8x8x7) prior in the one-step GAN (ablation)One-Step · DeepFashion attribute detection on synthesized imagesmAP (%): 72.4 -> 73.3No clear effect
add compositional mapping, T-Shirt attribute (ablation)Non-Compositional · DeepFashion attribute detection on synthesized images (Has T-Shirt)AP (%): 54.7 -> 63.2Improved
add compositional mapping, Has Long Pants (ablation)Non-Compositional · DeepFashion attribute detection on synthesized images (Has Long Pants)AP (%): 84.4 -> 90.7Improved
FashionGAN versus real image upper boundFashionGAN · DeepFashion attribute detection on synthesized imagesmAP (%): 86.8 -> 82.6Hurt
FashionGAN versus other methods in user ranking (2D non-parametric)2D Non-Parametric · User study rankingmean rank: 2.286 -> 1.544Improved
add compositional mapping in user ranking (ablation)Non-Compositional · User study rankingmean rank: 3.045 -> 1.544Improved
generated segmentation maps vs real maps fool volunteersFashionGAN shape generator · User study: segmentation mapsmisclassification rate: 42%Improved

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