Vesuvius Surface Detection

Introduction

Vesuvius Challenge is a competition that introduces a series of problems related to machine learning, computer vision and geometry. The competition is built to encourage community to develop solution used to aid in the recovery of ancient scrolls retrieved from the Vesuvius volcano.

Theere are many solutions proposed such as this and this. Currently, the Vesuvius Challenge host is solving 2 problems: Ink detection and Surface Detection for representation.

Datasets

- train_images/: contains 3D CT scan images of some parts of the scroll 
    - 1004283650.tif 
    - ...
- train_labels/
    - 1004283650.tif
    - ...
- test_images/: containing public and private test images 
    - 1407735.tif (only public test is availble, private test is available when submitting a notebook)
- train.csv: containing scroll_id and train images' id to map from CT scan image to real scroll
- test.csv: same as train.csv but for test images

Pipeline and trials

2.5D UNet approach

To be updated

nnUNetv2 approach

To be updated

Some trials

To be updated when I have