Supervised Reconstruction for Silhouette Tomography
This work addresses a novel tomography formulation for imaging applications, but appears incremental as it builds on existing deep learning techniques without broad validation.
The paper tackles the problem of silhouette tomography, a new X-ray computed tomography formulation using only imaging system geometry, by proposing a supervised deep neural network reconstruction method, and demonstrates its effectiveness on a synthetic dataset.
In this paper, we introduce silhouette tomography, a novel formulation of X-ray computed tomography that relies only on the geometry of the imaging system. We formulate silhouette tomography mathematically and provide a simple method for obtaining a particular solution to the problem, assuming that any solution exists. We then propose a supervised reconstruction approach that uses a deep neural network to solve the silhouette tomography problem. We present experimental results on a synthetic dataset that demonstrate the effectiveness of the proposed method.