Corpus ID: 14853973

Learning Typographic Style

@article{Baluja2016LearningTS,
  title={Learning Typographic Style},
  author={Shumeet Baluja},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.04000}
}
Typography is a ubiquitous art form that affects our understanding, perception, and trust in what we read. Thousands of different font-faces have been created with enormous variations in the characters. In this paper, we learn the style of a font by analyzing a small subset of only four letters. From these four letters, we learn two tasks. The first is a discrimination task: given the four letters and a new candidate letter, does the new letter belong to the same font? Second, given the four… Expand
Generating Chinese Typographic and Handwriting Fonts from a Small Font Sample Set
TLDR
A neural network architecture for Chinese fonts conversion is proposed, which directly uses images as inputs and is capable of converting Chinese-character fonts into fonts that are similar to the original fonts. Expand
Chinese Typography Transfer
TLDR
A new network architecture for Chinese typography transformation based on deep learning that can synthesize realistic-looking target typography from any source typography both on printed style and handwriting style and adopts end-to-end training without pre-trained used in other deep models. Expand
Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
TLDR
This paper proposes a novel framework named Style-Aware Variational Auto-Encoder (SA-VAE) to flexibly generate Chinese characters to capture the different characteristics of a Chinese character by disentangling the latent features into content-related and style-related components. Expand
EasyFont: A Style Learning-Based System to Easily Build Your Large-Scale Handwriting Fonts
TLDR
Using the proposed EasyFont system, for the first time, the practical handwriting font library in a user’s personal style with arbitrarily large numbers of Chinese characters can be generated automatically. Expand
Typeface Completion with Generative Adversarial Networks
TLDR
A Typeface Completion Network (TCN) which takes one character as an input, and automatically completes the entire set of characters in the same style as the input characters, which outperforms recently proposed state-of-the-art models for image-to-image translation. Expand
Multi-content GAN for Few-Shot Font Style Transfer
TLDR
This work focuses on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface, and proposes an end-to-end stacked conditional GAN model considering content along channels and style along network layers. Expand
Korean Font Synthesis with GANs
Font synthesis for CJK based languages that consists of large number of characters and complex structures is still a major challenge and ongoing research problem for computer vision and AI. In thisExpand
Dual Learning of the Generator and Recognizer for Chinese Characters
TLDR
A dual learning framework of offline Chinese character generator (G) and recognizer (R) based on deep models that can significantly improve both the recognition performance of R and the generation performance of G with high-resolution details for the adaptation of the unseen font styles. Expand
JointFontGAN: Joint Geometry-Content GAN for Font Generation via Few-Shot Learning
TLDR
This paper designs an end-to-end deep learning based approach for font generation through the new multi-stream extended conditional generative adversarial network (XcGAN) models, which jointly learn and generate both font skeleton and glyph representations simultaneously. Expand
Restore the Incomplete Calligraphy Based on Style Transfer
TLDR
The experimental results show that the Densenet-pix2pix model based style transfer method can effectively restore the remaining calligraphy characters, and the generated Chinese characters are more delicate. Expand
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Recognizing Image Style
TLDR
An approach to predicting style of images, and a thorough evaluation of different image features for these tasks, find that features learned in a multi-layer network generally perform best -- even when trained with object class (not style) labels. Expand
Defining Pictorial Style: Lessons from Linguistics and Computer Graphics
TLDR
It is suggested that descriptions of style of this kind can be thought of as hypotheses about the nature of the implicit rules that generated the pictures to which they were applied by embodying such stylistic rules in computer graphics programs. Expand
From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
TLDR
This network is a modified variational autoencoder that supports supervised training of single-image analogies and in-network evaluation of outputs with a structured similarity objective that captures pixel covariances. Expand
A Neural Algorithm of Artistic Style
TLDR
This work introduces an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality and offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery. Expand
Separating Style and Content with Bilinear Models
TLDR
A general framework for learning to solve two-factor tasks using bilinear models, which provide sufficiently expressive representations of factor interactions but can nonetheless be fit to data using efficient algorithms based on the singular value decomposition and expectation-maximization are presented. Expand
The Interestingness of Images
TLDR
This work introduces a set of features computationally capturing the three main aspects of visual interestingness and builds an interestingness predictor from them, shown on three datasets with varying context, reflecting the prior knowledge of the viewers. Expand
Elements of style
TLDR
This work introduces the first structure-transcending style similarity measure and validate it to be well aligned with human perception of stylistic similarity, and employs crowdsourcing to quantify the different components of this measure. Expand
Treasury of alphabets and lettering : a source book of the best letter forms of past and present for sign painters, graphic artists, commercial artists, typographers, printers, sculptors, architects, and schools of art and design
Lettering as a work of art good and bad letters the older letter forms recent letter forms classification and nomenclature of basic letter forms the use of capitals word spacing of capitals lineExpand
Representing Musical Genre: A State of the Art
TLDR
This article discusses the various approaches in representing musical genre, and proposes to classify these approaches in three main categories: manual, prescriptive and emergent approaches. Expand
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual RecognitionExpand
...
1
2
3
4
5
...