A U-Net trained only on physics-simulated synthetic TIE phase maps removes low-frequency artifacts from real 25,000 fps recordings of transient gas flows, yielding large reported gains in signal-to-background ratio and structural sharpness.
On the use of deep learning for phase recovery
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-Informed Synthetic Dataset and Denoising TIE-Reconstructed Phase Maps in Transient Flows Using Deep Learning
A U-Net trained only on physics-simulated synthetic TIE phase maps removes low-frequency artifacts from real 25,000 fps recordings of transient gas flows, yielding large reported gains in signal-to-background ratio and structural sharpness.