We describe an approach to blind 3D reconstruction that combines AI-based assessment of the scene with local optimization for accurate reconstruction. This enables global optimization that does not require accurate ground truth in calibration or a good starting point for
Model-based machine learning for computational reconstruction of opacity and missing information
Model-based machine learning methods incorporate domain knowledge from the physical forward model of an inverse problem to reduce the need for training data. In this research, we show how this can be used to address challenging limitations such as occlusion.
Focus optimization in a Computational Confocal Microscope
In this report we consider the numerical optimization of performance for a computational extension of a confocal microscope. Using a system where the pinhole detector is replaced with a detector array, we seek to exploit this additional information for each