AIbase
Product LibraryTool Navigation

ocr-vqgan

Public

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

Creat2022-11-07T22:45:21
Update2025-03-21T15:50:31
https://arxiv.org/abs/2210.11248
80
Stars
1
Stars Increase