BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation

Yuyang Peng; Shishi Xiao; Keming Wu; Qisheng Liao; Bohan Chen; Kevin Lin; Danqing Huang; Ji Li; Yuhui Yuan

doi:10.1109/cvpr52734.2025.02199

CVPR2025顶会

BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation

Yuyang Peng, Shishi Xiao, Keming Wu, Qisheng Liao, Bohan Chen, Kevin Lin, Danqing Huang, Ji Li, Yuhui Yuan

arXiv DOI 出版方

2025年份

9顶会引用

摘要

https://bizgen-msra.github.io (a) 386 characters / OCR: 93% (b) 426 characters / OCR: 96% (c) 545 characters / OCR: 99% (d) 594 characters / OCR: 99% (e) 737 characters / OCR: 97% Figure 1. Accurate article-level visual text rendering results in infographics generated with BizGen, ranging from 386 to 737 characters.