Artistic Arbitrary Style Transfer

TL;DR

This paper introduces an artistic style transfer method that combines foreground extraction with style transfer using CNNs, resulting in more consistent and artistically styled images by integrating object detection and style application.

Contribution

It proposes a novel approach that integrates foreground extraction via Detectron 2 with style transfer using SANet, enhancing style transfer quality and content preservation.

Findings

Improved style transfer consistency on complex images

Effective integration of object detection with style transfer

Enhanced preservation of content structure during stylization

Abstract

Arbitrary Style Transfer is a technique used to produce a new image from two images: a content image, and a style image. The newly produced image is unseen and is generated from the algorithm itself. Balancing the structure and style components has been the major challenge that other state-of-the-art algorithms have tried to solve. Despite all the efforts, it's still a major challenge to apply the artistic style that was originally created on top of the structure of the content image while maintaining consistency. In this work, we solved these problems by using a Deep Learning approach using Convolutional Neural Networks. Our implementation will first extract foreground from the background using the pre-trained Detectron 2 model from the content image, and then apply the Arbitrary Style Transfer technique that is used in SANet. Once we have the two styled images, we will stitch the two chunks of images after the process of style transfer for the complete end piece.