paper-image-extractor

Extract figures from papers via arXiv sources or PDF fallback.

Updated Aug 27, 2026

Search Tags:#research #multimodal #arxiv #figures #paper #image-extraction

Ready to run

npx skills add https://github.com/unstun/dqn10 --skill paper-image-extractor-unstun

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: paper-image-extractor
Source: https://github.com/unstun/dqn10/tree/main/.claude/skills/paper-image-extractor
Command: npx skills add https://github.com/unstun/dqn10 --skill paper-image-extractor-unstun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyMuPDF, requests, and includes scripts (resource) components.

What problem does it solve?

Extract figures from papers, prioritizing arXiv source packages to obtain high-quality images for reuse in research, presentations, and analyses.

Core Features & Use Cases

Prioritized extraction from arXiv source packages (pics, figures, fig, images, img) to obtain real paper images.
Fallback strategies: extract from embedded PDFs when arXiv sources are unavailable, and convert PDF figures when needed.
Output includes image files and an index detailing file names, sources, and sizes for traceability in literature workflows.

Quick Start

Run the tool to extract all figures from the target paper, prioritizing arXiv source packages.

Frequently Asked Questions about paper-image-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract figures from an arXiv paper for my research presentation?▼

To extract figures from an arXiv paper, the tool prioritizes arXiv source packages to locate high-quality images in folders like pics, figures, or images. It falls back to extracting embedded images directly from the PDF using PyMuPDF when sources are unavailable.

What is the best way to get high-quality images from cs-ai and vision papers?▼

The best way to get high-quality images from cs-ai and vision papers is by prioritizing arXiv source package extraction. This retrieves original real paper images from source folders instead of lower-resolution embedded PDF figures, ensuring optimal quality for reuse.

Can I extract embedded PDF figures when the arXiv source is unavailable?▼

Yes, you can extract embedded PDF figures when arXiv sources are unavailable. The tool uses PyMuPDF as a fallback strategy to extract images directly from the PDF file and can convert PDF figures when needed for your research workflow.

Does the extracted paper image output include an index for traceability?▼

Yes, the extracted paper image output includes an index for traceability. The generated index details file names, sources, and sizes, allowing you to track the origin of each figure within your literature workflows.

What are the limitations of extracting images directly from a PDF instead of an arXiv source?▼

Extracting images directly from a PDF instead of an arXiv source may yield lower image quality since it pulls embedded figures rather than original source files. PDF extraction via PyMuPDF serves as a fallback when source packages are inaccessible.