# Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction

arXiv: https://arxiv.org/abs/2411.19224 · HTML: https://mlsanity.com/paper/2411.19224/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 8 of 8)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [Structure-Aware Sparse-View X-ray 3D Reconstruction](https://mlsanity.com/paper/2311.10959/) (2023)
- [Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.06681/) (2023)
- [Fast Auto-Differentiable Digitally Reconstructed Radiographs for Solving Inverse Problems in Intraoperative Imaging](https://mlsanity.com/paper/2208.12737/) (2022)
- [Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering](https://mlsanity.com/paper/2312.06358/) (2023)
- [A Cone-Beam X-Ray CT Data Collection designed for Machine Learning](https://mlsanity.com/paper/1905.04787/) (2019)

## Built on by (most cited first, 3 of 3)

- [Grids Often Outperform Implicit Neural Representations at Compressing Dense Signals](https://mlsanity.com/paper/2506.11139/) (2025)
- [Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization](https://mlsanity.com/paper/2509.06890/) (2025)
- [Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registration](https://mlsanity.com/paper/2607.23343/) (2026)

## Abstract (arXiv)

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.