Attribute2Font

Font design is now still considered as an exclusive privilege of professional designers, whose creativity is not possessed by existing software systems. Nevertheless, we also notice that most commercial font products are in fact manually designed by following specific requirements on some attributes of glyphs, such as italic, serif, cursive, width, angularity, etc. Inspired by this fact, we propose a novel model, Attribute2Font, to automatically create fonts by synthesizing visually-pleasing glyph images according to user-specified attributes and their corresponding values. To the best of our knowledge, our model is the first one in the literature which is capable of generating glyph images in new font styles, instead of retrieving existing fonts, according to given values of specified font attributes. Specifically, Attribute2Font is trained to perform font style transfer between any two fonts conditioned on their attribute values. After training, our model can generate glyph images in accordance with an arbitrary set of font attribute values. Furthermore, a novel unit named Attribute Attention Module is designed to make those generated glyph images better embody the prominent font attributes. Considering that the annotations of font attribute values are extremely expensive to obtain, a semi-supervised learning scheme is also introduced to exploit a large number of unlabeled fonts. Experimental results demonstrate that our model achieves impressive performance on many tasks, such as creating glyph images in new font styles, editing existing fonts, interpolation among different fonts, etc.

[1]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[2]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Shiguang Shan,et al.  AttGAN: Facial Attribute Editing by Only Changing What You Want , 2017, IEEE Transactions on Image Processing.

[4]  Stephen DiVerdi,et al.  Learning A Stroke‐Based Representation for Fonts , 2018, Comput. Graph. Forum.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Lihi Zelnik-Manor,et al.  The Contextual Loss for Image Transformation with Non-Aligned Data , 2018, ECCV.

[7]  Douglas Eck,et al.  A Learned Representation for Scalable Vector Graphics , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Trevor Darrell,et al.  Multi-content GAN for Few-Shot Font Style Transfer , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[10]  Wenyu Liu,et al.  Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[11]  Xiao Liu,et al.  STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Aaron Hertzmann,et al.  Exploratory font selection using crowdsourced attributes , 2014, ACM Trans. Graph..

[13]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Hans-Peter Seidel,et al.  An intuitive control space for material appearance , 2016, ACM Trans. Graph..

[15]  Diego Gutierrez,et al.  A similarity measure for illustration style , 2014, ACM Trans. Graph..

[16]  Jianguo Xiao,et al.  Creating New Chinese Fonts based on Manifold Learning and Adversarial Networks , 2018, Eurographics.

[17]  Jan Kautz,et al.  Learning a manifold of fonts , 2014, ACM Trans. Graph..

[18]  Bo Zhao,et al.  EasyFont , 2018, ACM Trans. Graph..

[19]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[20]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[21]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[22]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[23]  Jianguo Xiao,et al.  DCFont: an end-to-end deep chinese font generation system , 2017, SIGGRAPH Asia Technical Briefs.

[24]  Jiebo Luo,et al.  Large-Scale Tag-Based Font Retrieval With Generative Feature Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Alla Sheffer,et al.  Analogy‐driven 3D style transfer , 2014, Comput. Graph. Forum.

[27]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.

[28]  Yue Jiang,et al.  SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks , 2019, AAAI.

[29]  Edward Y. Chang,et al.  RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[30]  Jianguo Xiao,et al.  Artistic glyph image synthesis via one-stage few-shot learning , 2019, ACM Trans. Graph..

[31]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[33]  Zhe Gan,et al.  AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[34]  Alla Sheffer,et al.  Elements of style , 2015, ACM Trans. Graph..

[35]  Thomas S. Huang,et al.  DeepFont: A System for Font Recognition and Similarity , 2015, ACM Multimedia.

[36]  Kiyoharu Aizawa,et al.  Assist Users' Interactions in Font Search with Unexpected but Useful Concepts Generated by Multimodal Learning , 2019, ICMR.

[37]  Yun Fu,et al.  Image Super-Resolution Using Very Deep Residual Channel Attention Networks , 2018, ECCV.