1 result found Sort:

joanrod
ocr-vqgan joanrod
0
67
unknown
2
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 VQGA...
ocr vqgan dataset ocr-vqgan paper2fig deep-learning paper2fig100k image-generation taming-transformers text-reconstruction image-reconstruction deep-generative-model
Created 2022-11-07
10 commits to master branch, last one about a year ago