extract-paper-images

Extract figures from arXiv papers by providing an arXiv ID to prioritize source images for maximum accuracy and quality. A three-tier pipeline captures high-resolution figures and saves them to an organized directory with a generated index.

Yes, you can extract images from a local PDF file. When arXiv source images are unavailable, the skill falls back to extracting embedded PDF figures and then performs raw PDF-based image extraction.

The best way to get high-quality images is using a tiered extraction approach that prioritizes arXiv source images over embedded PDF figures. This ensures maximum accuracy and resolution for research papers.

Yes, the image extraction tool requires PyMuPDF and requests. PyMuPDF handles parsing local PDF files while requests fetches arXiv source images during the extraction pipeline.

Extracted paper figures are organized under a structured directory path categorized by research domain and paper title. The skill creates an images folder per paper and outputs an index.md with provenance.

Extracted PDF images are lower quality because they are rendered or embedded versions of the original figures. Prioritizing arXiv source images captures original high-resolution files before PDF compression degrades them.