AI Paper Atlas

Research map / Image generation / Editing and style transfer

Image-Based CLIP-Guided Essence Transfer

Hila Chefer, Sagie Benaim, Roni Paiss, Lior Wolf

ECCV 2022 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 44 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 similarity loss (Eq. 5) (ablation)TargetCLIP optimizer · Essence transfer, celebrity targetssemantic scores (BLIP/CLIP)Improved
add L2 regularization on essence vector (ablation)TargetCLIP optimizer · Essence transfer, celebrity targetssource identity scoreImproved
add consistency loss (Eq. 6) (ablation)TargetCLIP optimizer · Essence transfer, celebrity targetssemantic scores (BLIP/CLIP)Improved
add consistency loss (Eq. 6) (ablation)TargetCLIP optimizer · Essence transfer, celebrity targetsidentity scoresHurt
increase number of training sources N to 4 or more (ablation)TargetCLIP optimizer and encoder · Essence transfer, celebrity targetsBLIP/CLIP semantic scoresImproved
use optimizer instead of encoderTargetCLIP · Essence transfer, celebrity targetsFID and target identity scoreImproved

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