Skip to content

ScrollPrize/villa

Repository files navigation

🏛️ villa

Vesuvius Challenge is a machine learning and computer vision competition to read the Herculaneum scrolls.
This repository contains the source code for Vesuvius Challenge: scroll tools, libraries, our website, data processing scripts, and more.


Libraries for Accessing Scrolls

A Python library for accessing CT scans of ancient scrolls.

A single-header C library for accessing CT scans of ancient scrolls.


Dataset & Rendering Tools

Tools to build/manage scroll datasets and cloud infrastructure.

Tools for flattening and rendering 3D mesh segments.

A GUI tool to inspect and label ink on virtually unwrapped segments of ancient scrolls.
Originally developed by Julian Schilliger.

The ink detection machine learning model used to win the Vesuvius Challenge 2023 Grand Prize.
Originally developed by Youssef Nader and Luke Farritor.


Automatic Segmentation Pipelines

An automatic segmentation pipeline to extract papyrus sheets from CT scans of ancient scrolls.
Originally developed by Julian Schilliger.


Supporting Resources

Source for the Vesuvius Challenge website.