paper-image-extractor

Extract figures from academic papers using arXiv source images.

Updated Apr 1, 2026

Search Tags:#multimodal #arxiv #image-extraction #research-workflow #figure-extraction #paper-image-extractor

Ready to run

npx skills add https://github.com/xiaoyu-ops/the_work_of_dedup --skill paper-image-extractor-xiaoyu-ops

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill helps researchers automatically extract figures from papers, prioritizing high-quality images from arXiv source packages to reduce manual screenshotting and quality loss.

Core Features & Use Cases

ArXiv-first extraction: Downloads arXiv source packages when available to locate genuine figures in common directories like pics/, figures/, fig/, images/, and img/.
PDF fallback extraction: If source images are unavailable, it can extract embedded figures from PDFs or replace with a best-effort pdf figure extraction.
Indexable outputs: Generates an index file detailing each image's path, size, and source, enabling reproducible workflows.

Quick Start

Supply a paper ID or local PDF and run the extractor to retrieve high-quality figures.

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 without losing image quality?▼

Extracting figures from an arXiv paper without quality loss is done by downloading the arXiv source package and locating original images in directories like pics/, figures/, or img/, bypassing PDF screenshot quality degradation.

What is the best way to get images from a research paper when the arXiv source is unavailable?▼

The best way to get images when the arXiv source is unavailable is using a PDF fallback extraction method. This process extracts embedded figures directly from the PDF file as a best-effort alternative to source images.

Can I extract figures from a local PDF file instead of an arXiv ID?▼

Yes, you can extract figures from a local PDF file. The extractor accepts a local PDF as input and uses PDF-based fallback extraction to retrieve embedded figures when arXiv source packages are not available or not provided.

Does PyMuPDF support extracting embedded images from academic PDFs?▼

Yes, PyMuPDF supports extracting embedded images from academic PDFs. It handles the PDF fallback extraction process, locating and pulling embedded figures directly from the document when high-quality arXiv source images are missing.

How are extracted paper images organized for reproducible research workflows?▼

Extracted paper images are organized for reproducible research workflows by generating an index file. This index details each image's file path, size, and source metadata, ensuring outputs are trackable and fully indexable.