harvardnlp/im2markup
older CNN-attention image-to-markup model; choose it for a lightweight, classic baseline instead of a ViT-based system
Neural model for converting Image-to-Markup (by Yuntian Deng yuntiandeng.com)
- 1.3k
- Lua
- MIT
dormant2.8y ago
lukas-blecher/LaTeX-OCR alternatives
math formula OCR / image-to-LaTeX
pix2tex: LaTeX OCR that converts images of math formulas into LaTeX code using a Vision Transformer (ViT).
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Listed as an alternative to
These projects were analysed and named LaTeX-OCR among their alternatives. The relationship is not symmetric — how LaTeX-OCR rates them is a separate judgement, made when LaTeX-OCR is analysed in its own right.
baidu/Unlimited-OCR
calls LaTeX-OCR “Equation-specific OCR; choose only for converting math images to LaTeX.”
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
24.3kPythonactive
zai-org/GLM-OCR
calls LaTeX-OCR “Use for converting equation images to LaTeX code, a focused subset.”
GLM-OCR: Accurate × Fast × Comprehensive
7.3kPythonactive