AI Paper Atlas

Research map / Image generation / Editing and style transfer

WISE: Whitebox Image Stylization by Example-Based Learning

Winfried Lötzsch, Max Reimann, Martin Büssemeyer, Amir Semmo, Jürgen Döllner, Matthias Trapp

ECCV 2022 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 3 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
train PPN with image-space loss instead of parameter-space loss (l1) (ablation)global PPN, XDoG · NPR benchmarkSSIM: 0.737 -> 0.780Improved
train PPN with image-space loss instead of parameter-space loss (l1) (ablation)global PPN, XDoG · NPR benchmarkPSNR: 12.927 -> 13.875Improved
image-space loss versus parameter-space loss on ground-truth parameter match (ablation)global PPN, XDoG · NPR benchmarkparameter l1 error: 0.158 -> 0.183Hurt
use multi-feature multi-head network instead of ResNet + multi-head (ablation)global PPN, XDoG · NPR benchmarkSSIM: 0.721 -> 0.780Improved
add differentiable XDoG with PPN (ResNet post-CNN) over CNN-only (ablation)APDrawing generator · APDrawingFID: 62.44 -> 60.55Improved
add differentiable XDoG with PPN (ResNet post-CNN) over CNN-only (ablation)APDrawing generator · APDrawingLPIPS: 0.275 -> 0.285No clear effect
replace fixed XDoG parameter preset with predicted PPN parameters (ablation)APDrawing generator · APDrawingFID: 71.56 -> 60.55Improved
use ResNet post-processing instead of U-Net (ablation)APDrawing generator · APDrawingFID: 89.93 -> 60.55Improved
add dropout (ablation)APDrawing generator, PPN + ResNet · APDrawingFID: 60.55 -> 71.92Hurt
initialize PPN backbone with ImageNet weights instead of random (ablation)APDrawing generator, ResNet · APDrawingFID: 60.55 -> 64.81Hurt
apply XDoG as post-processing instead of pre-processing (ablation)APDrawing generator · APDrawingtraining convergenceHurt
use PPN + XDoG alone without a post-processing CNN (ablation)APDrawing generator · APDrawingtraining stabilityHurt

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