Scalable Font Reconstruction with Dual Latent Manifolds
Nikita Srivatsan, Si Wu, Jonathan Barron, Taylor Berg-Kirkpatrick
Abstract
We propose a deep generative model that performs typography analysis and font reconstruction by learning disentangled manifolds of both font style and character shape. Our approach enables us to massively scale up the number of character types we can effectively model compared to previous methods. Specifically, we infer separate latent variables representing character and font via a pair of inference networks which take as input sets of glyphs that either all share a character type, or belong to the same font. This design allows our model to generalize to characters that were not observed during training time, an important task in light of the relative sparsity of most fonts. We also put forward a new loss, adapted from prior work that measures likelihood using an adaptive distribution in a projected space, resulting in more natural images without requiring a discriminator. We evaluate on the task of font reconstruction over various datasets representing character types of many languages, and compare favorably to modern style transfer systems according to both automatic and manually-evaluated metrics.- Anthology ID:
- 2021.emnlp-main.244
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3060–3072
- Language:
- URL:
- https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.emnlp-main.244/
- DOI:
- 10.18653/v1/2021.emnlp-main.244
- Cite (ACL):
- Nikita Srivatsan, Si Wu, Jonathan Barron, and Taylor Berg-Kirkpatrick. 2021. Scalable Font Reconstruction with Dual Latent Manifolds. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3060–3072, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Scalable Font Reconstruction with Dual Latent Manifolds (Srivatsan et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.emnlp-main.244.pdf