paper2fig

There are 0 repository under paper2fig topic.

joanrod / ocr-vqgan
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
dataset deep-generative-model deep-learning image-generation image-reconstruction ocr ocr-vqgan taming-transformers vqgan paper2fig paper2fig100k text-reconstruction
Language:Python 81
joanrod / paper2figure-dataset
Pipeline to create Paper2Fig dataset, a dataset for text-to-image generation from research papers and figures (e.g., diagrams of architectures or methods in fields like Machine Learning or Computer Vision)
dataset deep-generative-model deep-learning text-to-image arxiv-papers vqgan ocr-vqgan paper2fig paper2fig100k
Language:Python 3

joanrod / ocr-vqgan