Hierarchical Co-Embedding of Font Shapes and Impression Tags

• URL: http://arxiv.org/abs/2604.04158v1
• Date: Sun, 05 Apr 2026 15:55:40 GMT
• Title: Hierarchical Co-Embedding of Font Shapes and Impression Tags
• Abstract summary: Font shapes can evoke a wide range of impressions, but the correspondence between fonts and impression descriptions is not one-to-one.<n>We propose a hyperbolic co-embedding framework that models font--impression correspondence through entailment rather than simple paired alignment.
• Score: 7.423684794798727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Font shapes can evoke a wide range of impressions, but the correspondence between fonts and impression descriptions is not one-to-one: some impressions are broadly compatible with diverse styles, whereas others strongly constrain the set of plausible fonts. We refer to this graded constraint strength as style specificity. In this paper, we propose a hyperbolic co-embedding framework that models font--impression correspondence through entailment rather than simple paired alignment. Font images and impression descriptions, represented as single tags or tag sets, are embedded in a shared hyperbolic space with two complementary entailment constraints: impression-to-font entailment and low-to-high style-specificity entailment among impressions. This formulation induces a radial structure in which low style-specificity impressions lie near the origin and high style-specificity impressions lie farther away, yielding an interpretable geometric measure of how strongly an impression constrains font style. Experiments on the MyFonts dataset demonstrate improved bidirectional retrieval over strong one-to-one baselines. In addition, traversal and tag-level analyses show that the learned space captures a coherent progression from ambiguous to more style-specific impressions and provides a meaningful, data-driven quantification of style specificity.

Related papers

• Embedding Font Impression Word Tags Based on Co-occurrence [7.312180925669324]
  Different font styles convey distinct impressions, indicating a close relationship between font shapes and word tags describing those impressions.<n>This paper proposes a novel embedding method for impression tags that leverages these shape-impression relationships.
  arXiv  Detail & Related papers  (2025-08-26T09:02:17Z)
• Calligrapher: Freestyle Text Image Customization [72.71919410487881]
  Calligrapher is a novel diffusion-based framework that integrates advanced text customization with artistic typography.<n>By automating high-quality, visually consistent typography, Calligrapher surpasses traditional models.
  arXiv  Detail & Related papers  (2025-06-30T17:59:06Z)
• StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples [48.44036251656947]
  Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content.<n>We introduce StyleDistance, a novel approach to training stronger content-independent style embeddings.
  arXiv  Detail & Related papers  (2024-10-16T17:25:25Z)
• GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models [18.15911470339845]
  We introduce a diffusion-based method, termed ourmethod, to generate fonts that vividly embody specific impressions. Our experimental results, conducted on the MyFonts dataset, affirm that this method is capable of producing realistic, vibrant, and high-fidelity fonts.
  arXiv  Detail & Related papers  (2024-08-14T02:26:46Z)
• Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts [7.542892664684078]
  We propose Impression-CLIP, which is a novel machine-learning model based on CLIP (Contrastive Language-Image Pre-training) In our experiment, we perform cross-modal retrieval between fonts and impressions through co-embedding. The results indicate that Impression-CLIP achieves better retrieval accuracy than the state-of-the-art method.
  arXiv  Detail & Related papers  (2024-02-26T07:07:18Z)
• 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)
• Few-shot Font Generation by Learning Style Difference and Similarity [84.76381937516356]
  We propose a novel font generation approach by learning the Difference between different styles and the Similarity of the same style (DS-Font) Specifically, we propose a multi-layer style projector for style encoding and realize a distinctive style representation via our proposed Cluster-level Contrastive Style (CCS) loss.
  arXiv  Detail & Related papers  (2023-01-24T13:57:25Z)
• Font Generation with Missing Impression Labels [15.228202509283248]
  This paper proposes a font generation model that is robust against missing impression labels. Key ideas of the proposed method are (1)a co-occurrence-based missing label estimator and (2)an impression label space compressor. We proved that the proposed model generates high-quality font images using multi-label data with missing labels through qualitative and quantitative evaluations.
  arXiv  Detail & Related papers  (2022-03-19T16:02:54Z)
• Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets [56.018551958004814]
  This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources. Large-scale datasets with noisy image-text pairs provide a sub-optimal source of supervision. We propose to leverage and separate semantics and descriptive style through the incorporation of a style token and keywords extracted through a retrieval component.
  arXiv  Detail & Related papers  (2021-11-24T19:00:05Z)
• 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)
• Shared Latent Space of Font Shapes and Impressions [9.205278113241473]
  We realize a shared latent space where a font shape image and its impression words are embedded in a cross-modal manner. This latent space is useful to understand the style-impression correlation and generate font images by specifying several impression words.
  arXiv  Detail & Related papers  (2021-03-23T06:54:45Z)

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.