An Edge Filter Based Approach of Neural Style Transfer to the Image Stylization

Abstract

Transferring artistic styles onto any image or photograph has become popular in industry and academia in recent years. The use of neural style transfer (NST) for image style transfer is getting more popular. Convolution Neural Networks (CNN) based style transfer provides a new edge and life to the images, videos, and games. The re-rendering procedure of the content of one image with the style of another using various models and approaches is widely used for image style transfer. However, there are many drawbacks, including image quality, enormous loss, unrealistic artefacts, and the style of localized regions being less compared to the desired artistic style. For the reason that transfer technique fails to capture detailed, miniature textures and keep the true artwork's texture scales. We propose a multimodal CNN that stylizes hierarchically with several losses of increasing sizes while considering faithful representations of both colour and luminance channels. We may transfer not only large-scale, evident style cues but also subtle, exquisite ones by effectively handling style and texture cues at different sizes using various modalities. Our approach providing aesthetically pleasing results and is more comparable to multiple desirable creative styles using colour and texture cues at different scales.