TY  - EJOU
AU  - Kim, Bumsoo 
AU  - Shin, Wonseop 
AU  - Jung, Yonghoon 
AU  - Park, Youngsup 
AU  - Seo, Sanghyun 

TI  - Explicitly Color-Inspired Neural Style Transfer Using Patchified AdaIN
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2024
VL  - 141
IS  - 3
SN  - 1526-1506

AB  - 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.
KW  - Neural style transfer; image synthesis; image stylization

DO  - 10.32604/cmes.2024.056079