SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.00146 · CVPR · 2022

Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator

Lianwen Jin, Qiyuan Zhu, Nicholas Yuan, Yuxin Kong, Weihong Ma, Canjie Luo, Shenggao Zhu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kyxscut/CG-GAN — 1 of 4
FunctionStatusWhere it lives
CNN Ran kyxscut/CG-GAN/models/networks.py
pointer only (licence: NONE) · get_code("06d32a82871f6c23")
AttnDecoderRNN Not yet run kyxscut/CG-GAN/models/networks.py
pointer only (licence: NONE) · get_code("066187c8c2fcffd3")
AttnDecoderRNN_Cell Not yet run kyxscut/CG-GAN/models/networks.py
pointer only (licence: NONE) · get_code("7baf9a7f104a4128")
CAM_normD Not yet run kyxscut/CG-GAN/models/networks.py
pointer only (licence: NONE) · get_code("6cc5342e81c84980")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increases the difficulty to preserve local style patterns or detailed glyph structures. We investigate the drawbacks of previous studies and find that a coarsegrained discriminator is insufficient for supervising a font generator. To this end, we propose a novel Component-Aware Module (CAM), which supervises the generator to decouple content and style at a more fine-grained level, i.e., the component level. Different from previous studies struggling to increase the complexity of generators, we aim to perform more effective supervision for a relatively simple generator to achieve its full potential, which is a brand new perspective for font generation. The whole framework achieves remarkable results by coupling componentlevel supervision with adversarial learning, hence we call it Component-Guided GAN, shortly CG-GAN. Extensive experiments show that our approach outperforms state-of-theart one-shot font generation methods. Furthermore, it can be applied to handwritten word synthesis and scene text image editing, suggesting the generalization of our approach.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.00146")
get_code_for_paper("2205.00146")
have("2205.00146")

Connect an agent — have() is free.