Overview
Who this competition fits
Advanced CV practitioners experienced with 3D segmentation who want to push the state of the art in scroll unwrapping. Builds on the original Vesuvius ink detection challenge.
Read the original official blurb
Build a model to virtually unwrap ancient scrolls.
Preparation
From registration to a first submission
- 01
Python
- 02
deep learning (3D segmentation models)
- 03
volumetric image processing
- 04
surface reconstruction concepts
- 05
GPU training infrastructure
Before you commit: Requires building models to detect and segment papyrus surfaces in 3D CT scan volumes, then virtually unwrap them. Highly specialized domain with custom evaluation metric and demanding compute requirements.
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- Kaggle
- Last checked
- Nov 13, 2025