no code implementations • 31 May 2023 • Haisong Ding, Bozhi Luan, Dongnan Gui, Kai Chen, Qiang Huo
This model conditions on a printed glyph image and creates mappings between printed characters and handwritten images, thus enabling the generation of photo-realistic handwritten samples with diverse styles and unseen text contents.
1 code implementation • NeurIPS 2023 • Yukang Yang, Dongnan Gui, Yuhui Yuan, Weicong Liang, Haisong Ding, Han Hu, Kai Chen
We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text.
no code implementations • 25 May 2023 • Dongnan Gui, Kai Chen, Haisong Ding, Qiang Huo
Training from handwritten samples of a small character set, the DDPM is capable of mapping printed strokes to handwritten ones, which makes it possible to generate photo-realistic and diverse style handwritten samples of unseen character categories.
no code implementations • 15 Mar 2022 • Yangming Shi, Haisong Ding, Kai Chen, Qiang Huo
Style-guided text image generation tries to synthesize text image by imitating reference image's appearance while keeping text content unaltered.