OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from VQGAN in CompVis/taming-transformers
ocr
deep-learning
image-reconstruction
dataset
image-generation
deep-generative-model
taming-transformers
vqgan
ocr-vqgan
paper2fig
paper2fig100k
text-reconstruction
-
Updated
Jan 30, 2023 - Python