Reproduce “Segmentation of cracks in 3d images of fiber reinforced concrete using deep learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Anna Nowacka, Katja Schladitz, Szymon Grzesiak, Matthias Pahn
The authors train a 3D U-Net to segment cracks from CT volumes by labeling voxels as crack or background. They place simulated cracks in scans from four concrete types and use multiscale inference to handle wider real cracks. In qualitative tests on one steel-fiber and one polypropylene-fiber specimen, a 64-voxel patch was most consistent, but results lack ground-truth validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.