Adapting SAM for Volumetric X-Ray Data-sets of Arbitrary Sizes

no code implementations • 9 Feb 2024 • Roland Gruber, Steffen Rüger, Thomas Wittenberg

Objective: We propose a new approach for volumetric instance segmentation in X-ray Computed Tomography (CT) data for Non-Destructive Testing (NDT) by combining the Segment Anything Model (SAM) with tile-based Flood Filling Networks (FFN).

Computed Tomography (CT) Instance Segmentation +2

Instance Segmentation XXL-CT Challenge of a Historic Airplane

no code implementations • 5 Feb 2024 • Roland Gruber, Johann Christopher Engster, Markus Michen, Nele Blum, Maik Stille, Stefan Gerth, Thomas Wittenberg

Instance segmentation of compound objects in XXL-CT imagery poses a unique challenge in non-destructive testing.

Image Segmentation Instance Segmentation +2

An annotated instance segmentation XXL-CT data-set from a historic airplane

no code implementations • 16 Dec 2022 • Roland Gruber, Nils Reims, Andreas Hempfer, Stefan Gerth, Michael Böhnel, Theobald Fuchs, Michael Salamon, Thomas Wittenberg

To gain insights with respect to its history, design and state of preservation, a complete CT scan was obtained using an industrial XXL-computer tomography scanner.

Instance Segmentation Interactive Segmentation +1