A Closed-form Solution to Photorealistic Image Stylization

Abstract

Photorealistic image stylization concerns transferring style of a reference photo to a content photo with the constraint that the stylized photo should remain photorealistic. While several photorealistic image stylization methods exist, they tend to generate spatially inconsistent stylizations with noticeable artifacts. In this paper, we propose a method to address these issues. The proposed method consists of a stylization step and a smoothing step. While the stylization step transfers the style of the reference photo to the content photo, the smoothing step ensures spatially consistent stylizations. Each of the steps has a closed-form solution and can be computed efficiently. We conduct extensive experimental validations. The results show that the proposed method generates photorealistic stylization outputs that are more preferred by human subjects as compared to those by the competing methods while running much faster. Source code and additional results are available at https://github.com/NVIDIA/FastPhotoStyle .

arXiv commentAccepted by ECCV 2018

References in corpus (11)

• A Learned Representation For Artistic Style
• Learning Deconvolution Network for Semantic Segmentation
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Unsupervised Image-to-Image Translation Networks
• Unsupervised Cross-Domain Image Generation
• Texture Synthesis Using Convolutional Neural Networks
• Stacked What-Where Auto-encoders
• Deep Photo Style Transfer
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Visual Attribute Transfer through Deep Image Analogy
• Controlling Perceptual Factors in Neural Style Transfer

Cited by in corpus (17)

• Multimodal Unsupervised Image-to-Image Translation
• Neural Style Transfer: A Review
• Learning Linear Transformations for Fast Arbitrary Style Transfer
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• Photorealistic Style Transfer via Wavelet Transforms
• Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
• Text as Neural Operator: Image Manipulation by Text Instruction
• Rethinking and Improving the Robustness of Image Style Transfer
• Language-Driven Image Style Transfer
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation
• A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
• Semantic Attribute Matching Networks
• A Matching Algorithm based on Image Attribute Transfer and Local Features for Underwater Acoustic and Optical Images
• 3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations
• Neural Style Difference Transfer and Its Application to Font Generation
• Synthesizing New Retinal Symptom Images by Multiple Generative Models