Neural Vector Tomography for Reconstructing a Magnetization Vector Field
This work addresses reconstruction quality issues in vector tomography, which is incremental as it applies neural networks to an existing domain-specific problem.
The paper tackled the problem of artifacts and noise sensitivity in discretized vector tomographic reconstructions by modeling vector fields with smooth neural fields, resulting in high-quality reconstructions even under noise and substantially improved accuracy when underlying global continuous symmetry exists.
Discretized techniques for vector tomographic reconstructions are prone to producing artifacts in the reconstructions. The quality of these reconstructions may further deteriorate as the amount of noise increases. In this work, we instead model the underlying vector fields using smooth neural fields. Owing to the fact that the activation functions in the neural network may be chosen to be smooth and the domain is no longer pixelated, the model results in high-quality reconstructions, even under presence of noise. In the case where we have underlying global continuous symmetry, we find that the neural network substantially improves the accuracy of the reconstruction over the existing techniques.