CVApr 26, 2024

Few-shot Calligraphy Style Learning

arXiv:2404.17199v1h-index: 1
Originality Incremental advance
AI Analysis

This work addresses digital preservation of calligraphic art for cultural heritage digitization, representing an incremental advance in data-efficient generative modeling.

The paper tackled the problem of learning and replicating President Xu's calligraphy style with limited data, achieving comparable performance to traditional methods using under 200 images and reduced computational resources.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes