AI Paper Atlas

Research map / Image generation / Editing and style transfer

Neural Preset for Color Style Transfer

Zhanghan Ke, Yuhao Liu, Lei Zhu, Nanxuan Zhao, Rynson W.H. Lau

CVPR 2023 · 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
use Neural Preset instead of the strongest-ranked baseline, WCT²color style transfer · user studyaverage ranking: 2.67 -> 1.81Improved
use Neural Preset instead of PhotoWCT²color style transfer · 2K (2560 × 1440), RTX3090GPU inference time: 0.447\,s -> 0.016\,sImproved
use Neural Preset instead of PhotoWCT²color style transfer · 8K (7680 × 4320), RTX3090GPU memory: OOM -> 1.96\,GBImproved
use DNCM instead of the strongest baseline, CDTNetimage harmonization · iHarmony4MSE: 23.75 -> 24.31Hurt
use DNCM instead of CDTNetimage harmonization · iHarmony4PSNR: 38.23 -> 37.97Hurt
use DNCM instead of Learnable 3D LUTimage color enhancement · MIT-Adobe FiveKSSIM: 0.8636 -> 0.8697Improved
use DNCM instead of Learnable 3D LUTimage color enhancement · MIT-Adobe FiveKPSNR: 23.17 -> 23.12Hurt
replace DNCM with two CNNs for color mapping (ablation)Neural Preset self-supervised pipeline · color style transfertraining convergenceHurt
add the consistency loss L_con (ablation)Neural Preset · color style transfertraining convergenceImproved
reduce DNCM parameter dimension from k=16 to k=2 (ablation)Neural Preset · color style transfer validation setstyle similarity: 0.746 -> 0.128Hurt
increase DNCM parameter dimension from k=16 to k=32 (ablation)Neural Preset · color style transfer validation setstyle similarity: 0.746 -> 0.769Improved
increase DNCM patch size from 512 to 1024 (ablation)Neural Preset · 8K color style transferGPU memory: 1.96\,GB -> 2.14\,GBHurt

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