AI Paper Atlas

Research map / Image generation / Editing and style transfer

Sparse, Smart Contours to Represent and Edit Images

Tali Dekel, Chuang Gan, Dilip Krishnan, Ce Liu, William T. Freeman

CVPR 2018 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 81 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
replace a single GAN with the LFN-HFN cascade, using gradient features (ablation)image reconstruction from sparse contours · VGG FacesSSIM: 0.786 -> 0.812Improved
replace a single GAN with the LFN-HFN cascade, using gradient features (ablation)image reconstruction from sparse contours · CUB BirdsSSIM: 0.697 -> 0.740Improved
replace a single GAN with the LFN-HFN cascade, using gradient features (ablation)image reconstruction from sparse contours · Stanford DogsSSIM: 0.722 -> 0.749Improved
use learned features instead of gradient features (ablation)LFN-HFN contour reconstruction · VGG FacesSSIM: 0.812 -> 0.867Improved
use learned features instead of gradient features (ablation)LFN-HFN contour reconstruction · CUB BirdsSSIM: 0.740 -> 0.783Improved
use learned features instead of gradient features (ablation)LFN-HFN contour reconstruction · Stanford DogsSSIM: 0.749 -> 0.810Improved
use color features instead of gradient features (ablation)LFN-HFN contour reconstruction · VGG FacesSSIM: 0.812 -> 0.859Improved
use color features instead of gradient features (ablation)LFN-HFN contour reconstruction · CUB BirdsSSIM: 0.740 -> 0.763Improved
use color features instead of gradient features (ablation)LFN-HFN contour reconstruction · Stanford DogsSSIM: 0.749 -> 0.792Improved
use gradient features rather than learned features for contour edits (ablation)LFN-HFN image editing · edited imagesedit qualityImproved
use the dilated-patch discriminator instead of the patch discriminator (ablation)LFN-HFN reconstruction · sparse contour reconstructionreconstruction qualityImproved
add the HFN's adversarial training to the LFN reconstruction (ablation)LFN-HFN reconstruction · VGG Facestexture lossImproved

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