Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient and Scalable Chinese Vector Font Generation via Component Composition (2404.06779v1)

Published 10 Apr 2024 in cs.CV and cs.GR

Abstract: Chinese vector font generation is challenging due to the complex structure and huge amount of Chinese characters. Recent advances remain limited to generating a small set of characters with simple structure. In this work, we first observe that most Chinese characters can be disassembled into frequently-reused components. Therefore, we introduce the first efficient and scalable Chinese vector font generation approach via component composition, allowing generating numerous vector characters from a small set of components. To achieve this, we collect a large-scale dataset that contains over \textit{90K} Chinese characters with their components and layout information. Upon the dataset, we propose a simple yet effective framework based on spatial transformer networks (STN) and multiple losses tailored to font characteristics to learn the affine transformation of the components, which can be directly applied to the B\'ezier curves, resulting in Chinese characters in vector format. Our qualitative and quantitative experiments have demonstrated that our method significantly surpasses the state-of-the-art vector font generation methods in generating large-scale complex Chinese characters in both font generation and zero-shot font extension.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Svg vector font generation for chinese characters with transformer. In 2022 IEEE International Conference on Image Processing (ICIP), pages 646–650. IEEE, 2022.
  2. Learning a manifold of fonts. ACM Transactions on Graphics (ToG), 33(4):1–11, 2014.
  3. Deepsvg: A hierarchical generative network for vector graphics animation. Advances in Neural Information Processing Systems, 33:16351–16361, 2020.
  4. Unicode Consortium. The Unicode Standard. Unicode Consortium, Mountain View, CA, 9.0 edition, July 2016. Pages 689–692.
  5. A point set generation network for 3d object reconstruction from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 605–613, 2017.
  6. Automatic generation of chinese vector fonts via deep layout inferring. In SIGGRAPH Asia 2019 Technical Briefs, pages 33–36, 2019.
  7. Artistic glyph image synthesis via one-stage few-shot learning. ACM Transactions on Graphics (TOG), 38(6):1–12, 2019.
  8. Generative adversarial nets. In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014.
  9. Modeling the diffuse painting of ‘sumie’. Modeling in Computer Graphics, pages 329–338, 1991.
  10. Creating new chinese fonts based on manifold learning and adversarial networks. In Eurographics (Short Papers), pages 61–64, 2018.
  11. Diff-font: Diffusion model for robust one-shot font generation. arXiv preprint arXiv:2212.05895, 2022.
  12. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
  13. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  14. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017.
  15. Spatial transformer networks. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015.
  16. Scfont: Structure-guided chinese font generation via deep stacked networks. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 4015–4022, 2019.
  17. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  18. Look closer to supervise better: One-shot font generation via component-based discriminator. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13482–13491, 2022.
  19. Jintae Lee. Simulating oriental black-ink painting. IEEE Computer Graphics and Applications, 19(3):74–81, 1999.
  20. Cvfont: Synthesizing chinese vector fonts via deep layout inferring. In Computer Graphics Forum, volume 41, pages 212–225. Wiley Online Library, 2022.
  21. Fonttransformer: Few-shot high-resolution chinese glyph image synthesis via stacked transformers. Pattern Recognition, page 109593, 2023.
  22. A learned representation for scalable vector graphics. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7930–7939, 2019.
  23. Auto-encoder guided gan for chinese calligraphy synthesis. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), volume 1, pages 1095–1100. IEEE, 2017.
  24. Semantic image synthesis with spatially-adaptive normalization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2337–2346, 2019.
  25. Multiple heads are better than one: Few-shot font generation with multiple localized experts. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13900–13909, 2021.
  26. Im2vec: Synthesizing vector graphics without vector supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7342–7351, 2021.
  27. Deep unsupervised learning using nonequilibrium thermodynamics. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 2256–2265, Lille, France, 07–09 Jul 2015. PMLR.
  28. Steve Strassmann. Hairy brushes. ACM Siggraph Computer Graphics, 20(4):225–232, 1986.
  29. Pyramid embedded generative adversarial network for automated font generation. In 2018 24th International Conference on Pattern Recognition (ICPR), pages 976–981. IEEE, 2018.
  30. Example-based automatic font generation. In Smart Graphics: 10th International Symposium on Smart Graphics, Banff, Canada, June 24-26, 2010 Proceedings 10, pages 127–138. Springer, 2010.
  31. Fontrnn: Generating large-scale chinese fonts via recurrent neural network. In Computer Graphics Forum, volume 38, pages 567–577. Wiley Online Library, 2019.
  32. Yuchen Tian. zi2zi: Master chinese calligraphy with conditional adversarial networks. Internet] https://github. com/kaonashi-tyc/zi2zi, 3:2, 2017.
  33. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  34. Deepvecfont: Synthesizing high-quality vector fonts via dual-modality learning. ACM Transactions on Graphics (TOG), 40(6):1–15, 2021.
  35. Attribute2font: Creating fonts you want from attributes. ACM Transactions on Graphics (TOG), 39(4):69–1, 2020.
  36. Aesthetic text logo synthesis via content-aware layout inferring. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2436–2445, 2022.
  37. Deepvecfont-v2: Exploiting transformers to synthesize vector fonts with higher quality. arXiv preprint arXiv:2303.14585, 2023.
  38. Paul Yiu Chung Wong and Siu Chi Hsu. Designing chinese typeface using components. In Proceedings Nineteenth Annual International Computer Software and Applications Conference (COMPSAC’95), pages 416–421. IEEE, 1995.
  39. Vecfontsdf: Learning to reconstruct and synthesize high-quality vector fonts via signed distance functions. arXiv preprint arXiv:2303.12675, 2023.
  40. Automatic generation of artistic chinese calligraphy. IEEE Intelligent Systems, 20(3):32–39, 2005.
  41. Drawing and recognizing chinese characters with recurrent neural network. IEEE transactions on pattern analysis and machine intelligence, 40(4):849–862, 2017.
  42. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018.
  43. Separating style and content for generalized style transfer. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8447–8455, 2018.
  44. Ssnet: Structure-semantic net for chinese typography generation based on image translation. Neurocomputing, 371:15–26, 2020.
  45. Easy generation of personal chinese handwritten fonts. In 2011 IEEE international conference on multimedia and expo, pages 1–6. IEEE, 2011.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Jinyu Song (1 paper)
  2. Weitao You (4 papers)
  3. Shuhui Shi (6 papers)
  4. Shuxuan Guo (5 papers)
  5. Lingyun Sun (38 papers)
  6. Wei Wang (1793 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now