DCP-INN combines a diamond-shaped main network for low-frequency flow trends with a parallel correction network for high-frequency residuals, plus a Taylor-expansion high-order loss, to reconstruct hemodynamics accurately from sparse data in tortuous vessels.
Depth-aware guidance with self-estimated depth repre- sentations of diffusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.med-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dual-Correction Physics-Informed Neural Networks for Hemodynamic Reconstruction from Sparse Data
DCP-INN combines a diamond-shaped main network for low-frequency flow trends with a parallel correction network for high-frequency residuals, plus a Taylor-expansion high-order loss, to reconstruct hemodynamics accurately from sparse data in tortuous vessels.