Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction
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.
Code (3)
Tasks
3D ReconstructionDiagnosticNovel View SynthesisSimilar Papers 제목 키워드 기반
Neural Sparse Voxel Fields
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Rece…
NeRFSparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the pro…
Novel View SynthesisSparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertig…
3D Shape Generation3D Shape Modeling3D Shape RepresentationVoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every sample along each ray leads to slow renderin…
3D-Aware Image SynthesisImage GenerationNeural RenderingNovel View SynthesisSpNeRF: Memory Efficient Sparse Volumetric Neural Rendering Accelerator for Edge Devices
Neural rendering has gained prominence for its high-quality output, which is crucial for AR/VR applications. However, its large voxel grid data size and irregular access patterns challenge real-time processing on edge de…
Neural Rendering