A SIREN neural network with hand-tuned frequency scaling reconstructs pressure from noisy PIV/LPT data with lower error than OS-MODI and Green's function integration, and needs no mesh.
Charonko, Cameron V
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
-
Pressure Field Reconstruction with SIREN: A Mesh-Free Approach for Image Velocimetry in Complex Noisy Environments
A SIREN neural network with hand-tuned frequency scaling reconstructs pressure from noisy PIV/LPT data with lower error than OS-MODI and Green's function integration, and needs no mesh.