Physics-based Differentiable X-ray Rendering Improves Unsupervised 3D CBCT Reconstruction

Given 2D X-ray images of an object, we present a self-supervised framework for Cone-Beam Computed Tomography (CBCT) reconstruction by directly optimizing a 3D voxelgrid representation using physics-based differentiable X-ray rendering. Further, we investigate how the different formulations of X-ray image formation physics in the renderer affect the quality of 3D reconstruction and novel view synthesis. When combined with our regularized voxelgrid-based learning framework, we find that using an exact discretization of the Beer-Lambert law for X-ray attenuation in the renderer outperforms widely used iterative CBCT reconstruction algorithms, particularly when given only a few input views. As a result, we reconstruct high-fidelity 3D CBCT volumes from fewer X-rays, potentially reducing ionizing radiation exposure and improving diagnostic utility for practitioners.