AI Paper Atlas

Research map / Image generation / Editing and style transfer

Towards compact reversible image representations for neural style transfer

Xiyao Liu, Siyu Yang, Jian Zhang, Gerald Schaefer, Jiya Li, Xunli FAN, Songtao Wu, Hui Fang

ECCV 2024 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 0 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 InfoMinRev module, Barlow twins loss and JSD style loss together (ablation)flow baseline · style transfer, 1200 imagesSSIM: 0.372 -> 0.496Improved
add InfoMinRev module (ablation)full model without IMR · style transfer, 1200 imagesSSIM: 0.477 -> 0.496Improved
add Barlow twins channel-wise loss (ablation)full model without LB · style transfer, 1200 imagesSSIM: 0.459 -> 0.496Improved
use Jensen-Shannon divergence style loss instead of mean-variance L2 (ablation)full model · style transfer, 1200 imagesstyle loss: 0.836 -> 0.652Improved
add mutual information minimisation loss L_info (ablation)InfoMinRev flow · intermediate feature information distributioninformation in feature maps (bits)Improved
remove IMR and Barlow loss together (ablation)full model · style transfer, 1200 imagesstyle loss: 0.652 -> 0.566Mixed
propose method versus SANet and CAP-VSTNet on style lossOurs · style transfer, 1200 imagesstyle loss: 0.587 (SANet), 0.608 (CAP-VSTNet) vs 0.652Hurt
propose method versus CAP-VSTNet and ArtFlow on runtimeOurs · 512x512 imagestime (s): 0.096 -> 0.081Improved

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