Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning

Abstract

Automatic generation of artistic glyph images is a challenging task that attracts many research interests. Previous methods either are specifically designed for shape synthesis or focus on texture transfer. In this paper, we propose a novel model, AGIS-Net, to transfer both shape and texture styles in one-stage with only a few stylized samples. To achieve this goal, we first disentangle the representations for content and style by using two encoders, ensuring the multi-content and multi-style generation. Then we utilize two collaboratively working decoders to generate the glyph shape image and its texture image simultaneously. In addition, we introduce a local texture refinement loss to further improve the quality of the synthesized textures. In this manner, our one-stage model is much more efficient and effective than other multi-stage stacked methods. We also propose a large-scale dataset with Chinese glyph images in various shape and texture styles, rendered from 35 professional-designed artistic fonts with 7,326 characters and 2,460 synthetic artistic fonts with 639 characters, to validate the effectiveness and extendability of our method. Extensive experiments on both English and Chinese artistic glyph image datasets demonstrate the superiority of our model in generating high-quality stylized glyph images against other state-of-the-art methods.

arXiv commentAccepted by SIGGRAPH Asia 2019, code and datasets: https://hologerry.github.io/AGIS-Net/

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Conditional Image Synthesis With Auxiliary Classifier GANs
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• A guide to convolution arithmetic for deep learning
• Toward Multimodal Image-to-Image Translation
• Universal Style Transfer via Feature Transforms
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Image-to-image translation for cross-domain disentanglement
• Few-Shot Unsupervised Image-to-Image Translation
• FIGR: Few-shot Image Generation with Reptile
• From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
• Learning Typographic Style
• Arbitrary Style Transfer with Deep Feature Reshuffle

Cited by in corpus (6)

• ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach
• DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
• SketchPatch: Sketch Stylization via Seamless Patch-level Synthesis
• Attribute2Font: Creating Fonts You Want From Attributes
• Few-shot Compositional Font Generation with Dual Memory
• Few-Shot Font Generation with Deep Metric Learning