Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2404.17199 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909182975803392 |
|---|---|
| author | Chen, Fangda Nie, Jiacheng Jiang, Lichuan Zeng, Zhuoer |
| author_facet | Chen, Fangda Nie, Jiacheng Jiang, Lichuan Zeng, Zhuoer |
| contents | We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a two-stage training process. Initially, our model is pretrained on a diverse dataset containing works from various calligraphers. This is followed by fine-tuning on a smaller, specialized dataset of President Xu's calligraphy, comprising just under 200 images. Our method introduces innovative techniques of font image conditioning and stroke information conditioning, enabling the model to capture the intricate structural elements of Chinese characters. The effectiveness of our approach is demonstrated through a comparison with traditional methods like zi2zi and CalliGAN, with our model achieving comparable performance using significantly smaller datasets and reduced computational resources. This work not only presents a breakthrough in the digital preservation of calligraphic art but also sets a new standard for data-efficient generative modeling in the domain of cultural heritage digitization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17199 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-shot Calligraphy Style Learning Chen, Fangda Nie, Jiacheng Jiang, Lichuan Zeng, Zhuoer Computer Vision and Pattern Recognition We introduced "Presidifussion," a novel approach to learning and replicating the unique style of calligraphy of President Xu, using a pretrained diffusion model adapted through a two-stage training process. Initially, our model is pretrained on a diverse dataset containing works from various calligraphers. This is followed by fine-tuning on a smaller, specialized dataset of President Xu's calligraphy, comprising just under 200 images. Our method introduces innovative techniques of font image conditioning and stroke information conditioning, enabling the model to capture the intricate structural elements of Chinese characters. The effectiveness of our approach is demonstrated through a comparison with traditional methods like zi2zi and CalliGAN, with our model achieving comparable performance using significantly smaller datasets and reduced computational resources. This work not only presents a breakthrough in the digital preservation of calligraphic art but also sets a new standard for data-efficient generative modeling in the domain of cultural heritage digitization. |
| title | Few-shot Calligraphy Style Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17199 |