A Learned Representation For Artistic Style

Abstract

The diversity of painting styles represents a rich visual vocabulary for the construction of an image. The degree to which one may learn and parsimoniously capture this visual vocabulary measures our understanding of the higher level features of paintings, if not images in general. In this work we investigate the construction of a single, scalable deep network that can parsimoniously capture the artistic style of a diversity of paintings. We demonstrate that such a network generalizes across a diversity of artistic styles by reducing a painting to a point in an embedding space. Importantly, this model permits a user to explore new painting styles by arbitrarily combining the styles learned from individual paintings. We hope that this work provides a useful step towards building rich models of paintings and offers a window on to the structure of the learned representation of artistic style.

9 pages. 15 pages of Appendix, International Conference on Learning Representations (ICLR) 2017

Cited by in corpus (75)

• Guided Image Generation with Conditional Invertible Neural Networks
• Robust Motion In-betweening
• Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer
• Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
• High Fidelity Speech Synthesis with Adversarial Networks
• High-Fidelity Image Generation With Fewer Labels
• Domain Adaptation for Object Detection via Style Consistency
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Domain Generalization with MixStyle
• Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
• NeRF-VAE: A Geometry Aware 3D Scene Generative Model
• Learning to See: You Are What You See
• AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
• Style Mixer: Semantic-aware Multi-Style Transfer Network
• SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Improving One-stage Visual Grounding by Recursive Sub-query Construction
• Guided Image-to-Image Translation with Bi-Directional Feature Transformation
• Does enhanced shape bias improve neural network robustness to common corruptions?
• Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
• Style Example-Guided Text Generation using Generative Adversarial Transformers
• Image Morphing with Perceptual Constraints and STN Alignment
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations
• Generative Feature Replay For Class-Incremental Learning
• High-Resolution Network for Photorealistic Style Transfer
• Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
• Benefits of Linear Conditioning with Metadata for Image Segmentation
• Meta Feature Modulator for Long-tailed Recognition
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Self-labeled Conditional GANs
• Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer
• CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
• A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
• Score-Guided Generative Adversarial Networks
• Fast Universal Style Transfer for Artistic and Photorealistic Rendering
• Style-Aware Normalized Loss for Improving Arbitrary Style Transfer
• Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
• Deep Detail Enhancement for Any Garment
• Dance with Flow: Two-in-One Stream Action Detection
• Enhance Images as You Like with Unpaired Learning
• Frame Difference-Based Temporal Loss for Video Stylization
• A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation
• Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
• Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization
• Style is a Distribution of Features
• StyleRemix: An Interpretable Representation for Neural Image Style Transfer
• SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
• TinyGAN: Distilling BigGAN for Conditional Image Generation
• Omni-GAN: On the Secrets of cGANs and Beyond
• CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator
• Kunster -- AR Art Video Maker -- Real time video neural style transfer on mobile devices
• CIZSL++: Creativity Inspired Generative Zero-Shot Learning
• Multiple Style-Transfer in Real-Time
• A Method for Arbitrary Instance Style Transfer
• Robustness of Facial Recognition to GAN-based Face-morphing Attacks
• Learning Portrait Style Representations
• Recognizing Instagram Filtered Images with Feature De-stylization
• Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
• Restyling Images with the Bangladeshi Paintings Using Neural Style Transfer: A Comprehensive Experiment, Evaluation, and Human Perspective
• 3D Topology Transformation with Generative Adversarial Networks
• Photo style transfer with consistency losses
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence
• GPU-Accelerated Mobile Multi-view Style Transfer
• Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
• Unified Style Transfer
• Semantic Image Fusion
• Invertible Tone Mapping with Selectable Styles
• Lifelong Learning Process: Self-Memory Supervising and Dynamically Growing Networks
• Non-Parametric Neural Style Transfer
• Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
• Unaligned Image-to-Sequence Transformation with Loop Consistency
• Identifying and Exploiting Structures for Reliable Deep Learning
• Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier
• Image Translation via Fine-grained Knowledge Transfer
• Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation