Instance segmentation XXL-CT challenge of an historic airplane

The field of non-destructive testing (NDT) has been expanded in recent years with many new possibilities. Among other things, new methods of image segmentation (through the use of machine learning or artificial intelligence) and big data scenarios are gaining traction [1]. Together with the ADA Lovelace Center of the Fraunhofer IIS,  the Deutsches Museum in Munich and the German Society for Non-Destructive Testing (DGZFP) brings these two developments together as part of an (international) challenge and to answer the question [2]:


"Which automatic or interactive methods from the areas of digital image processing, machine learning or deep Neural networks can segment individual parts of a historic airplane with the highes quality?"


The challenge is divided into several phases (see Terms and conditions and below). After a training phase in which we provide known pairs of input sub-volumes and their manual annotations, the goal is to segment an unseen dataset for which we will not provide reference data. We will then evaluate and compare the results of the submitted segmentations with the manually obtained reference segmentation.

Sementic overview of the data aquisition and segmentation process


Phase 0 (Preparation)

  • Website is online
  • Registration is open
  • Example data is provided for download
  • We open a discussion forum for registered participants

Phase 1 (Training)

  • Starts 2023-02-15
  • Each registered participant can download a set of seven 512x512x512 sub-volumes and their corresponding reference segmentation (which may not be redistributed during the duration of the challenge)

Phase 2 (Testing)

  • Starts 2023-05-01
  • Registration closes
  • We provide an additional sub-volume without corresponding reference.
  • Submission period of segmentation and a brief description (1-2 pages) about their utilized methodology

Phase 3 (Evaluation)

  • Starts 2023-05-08
  • Submission closes
  • We evaluate the submissions
  • We will select and present the best solutions

Phase 4 (Publication)

  • Starts summer 2023
  • A joint publication is created (with participants as co-authors)

Phase 5 (End)

  • Discussion forum and website closes

Download a free example

Organisation and Administration

ADA Lovelace Center

  • Nadine Chrobok-Pensky
  •  Anikó Enderlein
  •  Svenja Seitz

Fraunhofer EZRT

  • Overall: Thomas Wittenberg, Stefan Gerth
  • Technical: Roland Gruber, Michael Salamon


  • Thomas Wenzel
  • Marika Maniszewski

Deutsches Museum, Munich

  • Andreas Hempfer

Scientific Committee

  • PD Dr. Thomas Wittenberg (Fraunhofer IIS, FAU Erlangen)
  • Prof. Dr. Tomas Sauer (Univ. Passau, Fraunhofer IIS)
  • Dr. Thomas Wenzel (DGZfP)
  • Prof. Dr. Thorsten Buzug  (Univ. Lübeck, Fraunhofer IMTE)


[1] Gruber R., Reims N, Hempfer A., Gerth S., Salamon M., Wittenberg T., 2022. An annotated instance segmentation XXL-CT dataset from a historic airplane,

[2] Gruber, R., Gerth, S., Claußen, J., Wörlein, N., Uhlmann, N., Wittenberg, T., 2020. Exploring Flood Filling Networks for Instance Segmentation of XXL-Volumetric and Bulk Material CT Data. Journal of Nondestructive Evaluation 40,