A U-Net with an embedded Graph Neural Network bottleneck improves segmentation consistency for L-PBF lattice structures under photometric variability by modeling spatial region dependencies rather than pixel-wise features.
C., Hagenbuchner, M., & Monfardini, G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph-augmented Segmentation of Complex Shapes in Laser Powder bed Fusion for Enhanced In Situ Inspection
A U-Net with an embedded Graph Neural Network bottleneck improves segmentation consistency for L-PBF lattice structures under photometric variability by modeling spatial region dependencies rather than pixel-wise features.