AI Paper Atlas

Research map / Image generation / Editing and style transfer

CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

Zijie Wu, Zhen Zhu, Junping Du, Xiang Bai

ECCV 2022 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 133 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 CCPL to SCTNet (ablation)SCTNet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)temporal loss (i=10): 12.22 -> 5.08Improved
add CCPL to SCTNet (ablation)SCTNet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)LPIPS (i=10): 0.446 -> 0.367Improved
add CCPL to SCTNet (ablation)SCTNet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)SIFID: 2.29 -> 2.43Hurt
add CCPL to SCTNet (ablation)SCTNet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)human preference (Vid): 0.060 -> 0.138Improved
add CCPL to AdaIN (ablation)AdaIN · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)temporal loss (i=10): 7.92 -> 6.72Improved
add CCPL to SANet (ablation)SANet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)temporal loss (i=10): 13.72 -> 7.09Improved
add CCPL to Linear (ablation)Linear · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)temporal loss (i=10): 7.61 -> 6.96Improved
add CCPL to AdaIN, SANet and Linear (ablation)AdaIN/SANet/Linear · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)SIFID: 2.44 -> 2.58; 2.40 -> 2.60; 2.38 -> 2.47Hurt
add L_nor instead of CCPL to SCTNet (ablation)SCTNet · Video/artistic style transfer (MS-COCO+WikiArt trained, MPI Sintel)temporal loss (i=10): 12.22 -> 11.54No clear effect
add CCPL to SCTNet (ablation)SCTNet · Photo-realistic style transferLPIPS: 0.427 -> 0.351Improved
add CCPL to SCTNet (ablation)SCTNet · Photo-realistic style transferSIFID: 1.65 -> 2.14Hurt
add CCPL to SCTNet (ablation)SCTNet · Photo-realistic style transferhuman preference: 0.128 -> 0.262Improved

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