A differentiable physics-informed gradient descent framework for CTR phase retrieval matches traditional methods in fidelity on synthetic data while enabling seamless inclusion of complex experimental effects and multi-diagnostic constraints.
Phase imaging with an untrained neural network
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A genetically programmed iterative algorithm reconstructs complex amplitude and phase objects from a single lensless intensity measurement by jointly estimating amplitude, phase, and propagation distance.
citing papers explorer
-
Adaptable phase retrieval for coherent transition radiation spectroscopy based on differentiable physics information
A differentiable physics-informed gradient descent framework for CTR phase retrieval matches traditional methods in fidelity on synthetic data while enabling seamless inclusion of complex experimental effects and multi-diagnostic constraints.
-
Single-Shot Lensless Imaging with Physics Guided Genetic Programming
A genetically programmed iterative algorithm reconstructs complex amplitude and phase objects from a single lensless intensity measurement by jointly estimating amplitude, phase, and propagation distance.