Differentiable Uncalibrated Imaging

We will present our paper 'Differentiable Uncalibrated Imaging' where we propose a differentiable imaging framework to address uncertainty in measurement coordinates, such as sensor locations and projection angles. Our approach leverages implicit neural networks and spline-based neural fields to perform joint calibration and image reconstruction. This makes it possible, for example, to use pre-trained neural networks to configurations different from those for which they were originally trained. We will begin by presenting the general optimization framework underlying our method. Next, we will illustrate our approach to 2D and 3D computed tomography, and show that it produces improved reconstructions compared to baselines that do not account for the lack of calibration. Finally, we will explore how this framework extends to the challenging problem of 3D cryo-tomography reconstruction, tackling scenarios with misaligned and noisy input projections.