Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
arXiv:1603.01768
Abstract
Convolutional neural networks (CNNs) have proven highly effective at image synthesis and style transfer. For most users, however, using them as tools can be a challenging task due to their unpredictable behavior that goes against common intuitions. This paper introduces a novel concept to augment such generative architectures with semantic annotations, either by manually authoring pixel labels or using existing solutions for semantic segmentation. The result is a content-aware generative algorithm that offers meaningful control over the outcome. Thus, we increase the quality of images generated by avoiding common glitches, make the results look significantly more plausible, and extend the functional range of these algorithms---whether for portraits or landscapes, etc. Applications include semantic style transfer and turning doodles with few colors into masterful paintings!
References in corpus (3)
Cited by in corpus (42)
- Neural Photo Editing with Introspective Adversarial Networks
- Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
- Neural Style Transfer: A Review
- Learning Linear Transformations for Fast Arbitrary Style Transfer
- Demystifying Neural Style Transfer
- Coherent Online Video Style Transfer
- Context-Aware Text-Based Binary Image Stylization and Synthesis
- Exploring the Neural Algorithm of Artistic Style
- High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
- Scribbler: Controlling Deep Image Synthesis with Sketch and Color
- Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles
- Automatic Semantic Style Transfer using Deep Convolutional Neural Networks and Soft Masks
- Stereoscopic Neural Style Transfer
- Unsupervised Person Image Generation with Semantic Parsing Transformation
- Controllable Artistic Text Style Transfer via Shape-Matching GAN
- Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
- Anisotropic Stroke Control for Multiple Artists Style Transfer
- Controlling Perceptual Factors in Neural Style Transfer
- ReCoNet: Real-time Coherent Video Style Transfer Network
- High-Resolution Network for Photorealistic Style Transfer
- Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
- A Closed-form Solution to Universal Style Transfer
- Quantitative Evaluation of Style Transfer
- Diversified Arbitrary Style Transfer via Deep Feature Perturbation
- Mask-Guided Portrait Editing with Conditional GANs
- Face Parsing via Recurrent Propagation
- Geometric Style Transfer
- Language-Driven Image Style Transfer
- Disentangling Structure and Appearance in ViT Feature Space
- Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
- ImagineNet: Restyling Apps Using Neural Style Transfer
- CNN based texture synthesize with Semantic segment
- A Pragmatic AI Approach to Creating Artistic Visual Variations by Neural Style Transfer
- TET-GAN: Text Effects Transfer via Stylization and Destylization
- Awesome Typography: Statistics-Based Text Effects Transfer
- CreativeBioMan: Brain and Body Wearable Computing based Creative Gaming System
- The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation
- Kunster -- AR Art Video Maker -- Real time video neural style transfer on mobile devices
- Neural Style Difference Transfer and Its Application to Font Generation
- TE141K: Artistic Text Benchmark for Text Effect Transfer
- Image Synthesis and Style Transfer
- Style Decomposition for Improved Neural Style Transfer