We present DiffVox, a self-supervised framework for Cone-Beam Computed Tomography (CBCT) reconstruction by directly optimizing a voxelgrid representation using physics-based differentiable X-ray rendering. Further, we investigate how the different implementations of the X-ray image formation model in the renderer affect the quality of 3D reconstruction and novel view synthesis. When combined with our regularized voxel-based learning framework, we find that using an exact implementation of the discrete Beer-Lambert law for X-ray attenuation in the renderer outperforms both widely used iterative CBCT reconstruction algorithms and modern neural field approaches, 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. Our implementation is available at https://github.com/hossein-momeni/DiffVox.
@article{arxiv.2411.19224,
title = {Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction},
author = {Mohammadhossein Momeni and Vivek Gopalakrishnan and Neel Dey and Polina Golland and Sarah Frisken},
journal= {arXiv preprint arXiv:2411.19224},
year = {2025}
}