Juan A. Rodriguez

Results 3 repositories owned by Juan A. Rodriguez

ocr-vqgan

72
Stars
1
Forks
Watchers

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...

star-vector

3.1k
Stars
162
Forks
Watchers

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textu...

figure-diffusion

37
Stars
4
Forks
37
Watchers

Generating figures from research papers, using textual captions from the paper.