A Multi-Implicit Neural Representation for Fonts

• URL: http://arxiv.org/abs/2106.06866v1
• Date: Sat, 12 Jun 2021 21:40:11 GMT
• Title: A Multi-Implicit Neural Representation for Fonts
• Authors: Pradyumna Reddy, Zhifei Zhang, Matthew Fisher, Hailin Jin, Zhaowen Wang, Niloy J. Mitra
• Abstract summary: font-specific discontinuities like edges and corners are difficult to represent using neural networks. We introduce textitmulti-implicits to represent fonts as a permutation-in set of learned implict functions, without losing features.
• Score: 79.6123184198301
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Fonts are ubiquitous across documents and come in a variety of styles. They are either represented in a native vector format or rasterized to produce fixed resolution images. In the first case, the non-standard representation prevents benefiting from latest network architectures for neural representations; while, in the latter case, the rasterized representation, when encoded via networks, results in loss of data fidelity, as font-specific discontinuities like edges and corners are difficult to represent using neural networks. Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce \textit{multi-implicits} to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e.g., edges and corners). However, while multi-implicits locally preserve font features, obtaining supervision in the form of ground truth multi-channel signals is a problem in itself. Instead, we propose how to train such a representation with only local supervision, while the proposed neural architecture directly finds globally consistent multi-implicits for font families. We extensively evaluate the proposed representation for various tasks including reconstruction, interpolation, and synthesis to demonstrate clear advantages with existing alternatives. Additionally, the representation naturally enables glyph completion, wherein a single characteristic font is used to synthesize a whole font family in the target style.

Related papers

• VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization [52.870638830417]
  We propose a VQGAN-based framework (i.e., VQ-Font) to enhance glyph fidelity through token prior refinement and structure-aware enhancement. Specifically, we pre-train a VQGAN to encapsulate font token prior within a codebook. Subsequently, VQ-Font refines the synthesized glyphs with the codebook to eliminate the domain gap between synthesized and real-world strokes.
  arXiv  Detail & Related papers  (2023-08-27T06:32:20Z)
• CF-Font: Content Fusion for Few-shot Font Generation [63.79915037830131]
  We propose a content fusion module (CFM) to project the content feature into a linear space defined by the content features of basis fonts. Our method also allows to optimize the style representation vector of reference images. We have evaluated our method on a dataset of 300 fonts with 6.5k characters each.
  arXiv  Detail & Related papers  (2023-03-24T14:18:40Z)
• VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functions [15.47282857047361]
  This paper proposes an end-to-end trainable method, VecFontSDF, to reconstruct and synthesize high-quality vector fonts. Based on the proposed SDF-based implicit shape representation, VecFontSDF learns to model each glyph as shape primitives enclosed by several parabolic curves.
  arXiv  Detail & Related papers  (2023-03-22T16:14:39Z)
• Diff-Font: Diffusion Model for Robust One-Shot Font Generation [110.45944936952309]
  We propose a novel one-shot font generation method based on a diffusion model, named Diff-Font. The proposed model aims to generate the entire font library by giving only one sample as the reference. The well-trained Diff-Font is not only robust to font gap and font variation, but also achieved promising performance on difficult character generation.
  arXiv  Detail & Related papers  (2022-12-12T13:51:50Z)
• Few-Shot Font Generation by Learning Fine-Grained Local Styles [90.39288370855115]
  Few-shot font generation (FFG) aims to generate a new font with a few examples. We propose a new font generation approach by learning 1) the fine-grained local styles from references, and 2) the spatial correspondence between the content and reference glyphs.
  arXiv  Detail & Related papers  (2022-05-20T05:07:05Z)
• XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation [13.569449355929574]
  We propose a self-supervised cross-modality pre-training strategy and a cross-modality transformer-based encoder. The encoder is conditioned jointly on the glyph image and the corresponding stroke labels. It only requires one reference glyph and achieves the lowest rate of bad cases in the few-shot font generation task 28% lower than the second best.
  arXiv  Detail & Related papers  (2022-04-11T13:34:40Z)
• Scalable Font Reconstruction with Dual Latent Manifolds [55.29525824849242]
  We propose a deep generative model that performs typography analysis and font reconstruction. Our approach enables us to massively scale up the number of character types we can effectively model. We evaluate on the task of font reconstruction over various datasets representing character types of many languages.
  arXiv  Detail & Related papers  (2021-09-10T20:37:43Z)
• Learning Implicit Glyph Shape Representation [6.413829791927052]
  We present a novel implicit glyph shape representation, which glyphs as shape primitives enclosed quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Based on the proposed representation, we design a simple yet effective disentangled network for the challenging one-shot font style transfer problem.
  arXiv  Detail & Related papers  (2021-06-16T06:42:55Z)
• Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character [10.236778478360614]
  The main purpose of this paper is to design a network framework that can extract and recombine the content and style of the characters. The paper combines various depth networks such as Convolutional Neural Network, Multi-layer Perceptron and Residual Network to find the optimal model. The result shows that those characters we have generated is very close to real characters, using Structural Similarity index and Peak Signal-to-Noise Ratio evaluation criterions.
  arXiv  Detail & Related papers  (2020-03-28T04:30:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.