search

yizhiwang96 / deepvecfont

[SIGGRAPH Asia 2021] DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
MIT License
182 stars 31 forks source link

Some questions about NDR #25

Open bwtine opened 1 year ago

bwtine commented 1 year ago

This is such an amazing project！ How did you pre-train the NDR model? What are the labels for the training set and the test set?Can the NDR you provide be used to generate vector English characters for each style? Do I need to retrain NDR for each style English Fonts? How to train my own NDR for icons or Chinese characteres？What are the labels for the training set and the test set? I hope to get your reply, thanks!!!

yizhiwang96 commented 1 year ago

Sorry for the late reply. NDR was designed to rasterize a drawing suquence (SVGs). If you learn a latent space from a datasets of SVGs, you can generate raster images of new fonts. The input is the drawing suquence processed by my code, the labels are the corresponding raster images. You can have a try!