Explicitly Color-Inspired Neural Style Transfer Using  

作　　者：Bumsoo Kim Wonseop Shin Yonghoon Jung Youngsup Park Sanghyun Seo 

机构地区：[1]Department of Applied Art and Technology,Chung-Ang University,Anseong,17546,Republic of Korea [2]Department of Advanced Imaging Science Multimedia&Film,Chung-Ang University,Seoul,06974,Republic of Korea [3]Innosimulation Co.,Ltd.,Gangseo-gu,07794,Republic of Korea [4]School of Art and Technology,Chung-Ang University,Anseong,17546,Republic of Korea

出　　处：《Computer Modeling in Engineering & Sciences》2024年第12期2143-2164,共22页工程与科学中的计算机建模（英文）

基　　金：supported by the National Research Foundation of Korea (NRF)grant funded by the Korean government (MSIT) (No.2022R1A2C1004657,Contribution Rate:50%);Culture,Sports and Tourism R&D Program through the Korea Creative Content Agency grant funded by Ministry of Culture Sports and Tourism in 2024 (Project Name:Developing Professionals for R&D in Contents Production Based on Generative Ai and Cloud,Project Number:RS-2024-00352578,Contribution Rate:50%).

摘　　要：Arbitrary style transfer aims to perceptually reflect the style of a reference image in artistic creations with visual aesthetics.Traditional style transfer models,particularly those using adaptive instance normalization(AdaIN)layer,rely on global statistics,which often fail to capture the spatially local color distribution,leading to outputs that lack variation despite geometric transformations.To address this,we introduce Patchified AdaIN,a color-inspired style transfer method that applies AdaIN to localized patches,utilizing local statistics to capture the spatial color distribution of the reference image.This approach enables enhanced color awareness in style transfer,adapting dynamically to geometric transformations by leveraging local image statistics.Since Patchified AdaIN builds on AdaIN,it integrates seamlessly into existing frameworks without the need for additional training,allowing users to control the output quality through adjustable blending parameters.Our comprehensive experiments demonstrate that Patchified AdaIN can reflect geometric transformations(e.g.,translation,rotation,flipping)of images for style transfer,thereby achieving superior results compared to state-of-the-art methods.Additional experiments show the compatibility of Patchified AdaIN for integration into existing networks to enable spatial color-aware arbitrary style transfer by replacing the conventional AdaIN layer with the Patchified AdaIN layer.

关 键 词：Neural style transfer image synthesis image stylization 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]