# Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning

Source: [Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning](<https://www.sota2.com/research/paper/68fa653c1e209131cea093db>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:22:52.893Z

Authors: Tomasz Konopczy\\'nski, Thorben Kr\\"oger, Lei Zheng, J\\"urgen Hesser

Published: 2019-01-04T09:53:07.000Z

## Abstract

We propose a novel approach for automatic extraction (instance segmentation) of fibers from low resolution 3D X-ray computed tomography scans of short glass fiber reinforced polymers. We have designed a 3D instance segmentation architecture built upon a deep fully convolutional network for semantic segmentation with an extra output for embedding learning. We show that the embedding learning is capable of learning a mapping of voxels to an embedded space in which a standard clustering algorithm can be used to distinguish between different instances of an object in a volume. In addition, we discuss a merging post-processing method which makes it possible to process volumes of any size. The proposed 3D instance segmentation network together with our merging algorithm is the first known to authors knowledge procedure that produces results good enough, that they can be used for further analysis of low resolution fiber composites CT scans.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1901.01034>)

[PDF](<https://arxiv.org/pdf/1901.01034.pdf>)