O

ocr-vqgan

🔧🔗https://github.com/joanrod/figure-diffusion Generating figures from research papers, using textual captions from the paper.

🔧🔗https://github.com/joanrod/ocr-vqganOCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-im