Style-Transfer via Texture-Synthesis

Abstract

Style-transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image which is an artistic mixture of the two. Recent work on this problem adopting Convolutional Neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained. There exists an alternative path towards handling the style-transfer task, via generalization of texture-synthesis algorithms. This approach has been proposed over the years, but its results are typically less impressive compared to the CNN ones. In this work we propose a novel style-transfer algorithm that extends the texture-synthesis work of Kwatra et. al. (2005), while aiming to get stylized images that get closer in quality to the CNN ones. We modify Kwatra's algorithm in several key ways in order to achieve the desired transfer, with emphasis on a consistent way for keeping the content intact in selected regions, while producing hallucinated and rich style in others. The results obtained are visually pleasing and diverse, shown to be competitive with the recent CNN style-transfer algorithms. The proposed algorithm is fast and flexible, being able to process any pair of content + style images.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Fast Patch-based Style Transfer of Arbitrary Style
• Preserving Color in Neural Artistic Style Transfer

Cited by in corpus (21)

• Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer
• Poison Ink: Robust and Invisible Backdoor Attack
• Neural Style Transfer: A Review
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Visual Attribute Transfer through Deep Image Analogy
• Context-Aware Text-Based Binary Image Stylization and Synthesis
• Meta Networks for Neural Style Transfer
• End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks
• Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
• Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
• NeuBTF: Neural fields for BTF encoding and transfer
• Region-aware Adaptive Instance Normalization for Image Harmonization
• Multimodal Style Transfer via Graph Cuts
• Shape-Texture Debiased Neural Network Training
• Neural Photometry-guided Visual Attribute Transfer
• Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image
• Line Artist: A Multiple Style Sketch to Painting Synthesis Scheme
• Semantic Example Guided Image-to-Image Translation
• Graphic Narrative with Interactive Stylization Design
• Learning to Transfer Visual Effects from Videos to Images
• Finite Differences in Forward and Inverse Imaging Problems--MaxPol Design