RieszNet, with 7,153 parameters, matches 3D U-Net performance for segmenting multiscale cracks in 3D concrete CT images when trained on semi-synthetic data.
In: DGZfP Jahrestagung 2021 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cracks in concrete
RieszNet, with 7,153 parameters, matches 3D U-Net performance for segmenting multiscale cracks in 3D concrete CT images when trained on semi-synthetic data.