A magnitude-index loss improves multi-scale reconstruction of PIV velocity fields in a U-Net inpainting task compared with MSE, while a hybrid loss trades off pixel accuracy.
TCC-III engine benchmark for large- eddy simulation of IC engine flows,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
physics.flu-dyn 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Vector-based loss functions for turbulent flow field inpainting
A magnitude-index loss improves multi-scale reconstruction of PIV velocity fields in a U-Net inpainting task compared with MSE, while a hybrid loss trades off pixel accuracy.