P^2-Gaussian: Prior-Driven and Projection-Guided Gaussian Splatting for Sparse-View Cone-Beam CT Reconstruction
Abstract
Sparse-view cone-beam computed tomography (CBCT) reconstruction reduces imaging dose and scan time, but severe angular undersampling makes the inverse problem highly ill-posed. Existing 3D Gaussian Splatting (3DGS) methods initialize Gaussian primitives from Feldkamp-Davis-Kress (FDK) reconstructions that are contaminated by streak artifacts. The limited angular coverage also leaves the Gaussian parameters underconstrained, producing needle-like artifacts. We propose P2-Gaussian, a prior-driven and projection-guided 3DGS framework. In this framework, a latent rectified flow model, Sparse2Prior, first restores the artifact-corrupted FDK volume into an anatomical prior in approximately 5 s. Gaussian primitives are then initialized from this prior in a tissue-adaptive manner, which yields a compact representation with 62%-65% fewer optimized primitives than random sampling. During optimization, virtual projections synthesized at intermediate angles between the measured projections are activated in rotation, while measured projections remain dominant in the objective function. Experiments on 5, 10 and 20 measured views showed that the proposed P2-Gaussian achieved the highest PSNR and SSIM among all methods. Compared with the optimization-based Gaussian baseline, our method increases PSNR by 5.98, 4.25 and 2.49 dB and accelerates reconstruction by 2.6-3.0 times. These results indicate that coupling a learned anatomical prior with measurement-constrained Gaussian optimization is effective for sparse-view CBCT reconstruction. Code is publicly available at: https://github.com/Ballbo5354/P-2-Gaussian.
Related
- DoReMe: Dual optimization of Reconstruction and Motion estimation for self-navigated free-breathing abdominal MRI using Gaussian Splatting
- Gaussian-splatting ptychography via explicit and interpretable primitives
- Scaling Density Functional Theory with Gaussian Splatting
- A differentiable Lagrangian-coupled 3D Gaussian Splatting-SPH model for forward simulation and inverse analysis in solid mechanics
- A Discretely Entropy Conserving/Stable Flux Reconstruction Scheme via Hybridized Split Form Differential Operator and Generalized Entropy Projection
BibTeX
@misc{xia2026p2gaussian,
title = {{P^2-Gaussian: Prior-Driven and Projection-Guided Gaussian Splatting for Sparse-View Cone-Beam CT Reconstruction}},
author = {Jinqiu Xia and Jianhui Ma and Bin Ouyang and Xiaoyan Huang and Yuan Xu and Zun Piao},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.39359},
eprint = {2610.39359},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.39359},
}
RIS
TY - UNPB
TI - P^2-Gaussian: Prior-Driven and Projection-Guided Gaussian Splatting for Sparse-View Cone-Beam CT Reconstruction
AU - Jinqiu Xia
AU - Jianhui Ma
AU - Bin Ouyang
AU - Xiaoyan Huang
AU - Yuan Xu
AU - Zun Piao
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.39359
UR - https://arxiv.org/abs/2610.39359
AB - Sparse-view cone-beam computed tomography (CBCT) reconstruction reduces imaging dose and scan time, but severe angular undersampling makes the inverse problem highly ill-posed. Existing 3D Gaussian Splatting (3DGS) methods initialize Gaussian primitives from Feldkamp-Davis-Kress (FDK) reconstructions that are contaminated by streak artifacts. The limited angular coverage also leaves the Gaussian parameters underconstrained, producing needle-like artifacts. We propose P2-Gaussian, a prior-driven and projection-guided 3DGS framework. In this framework, a latent rectified flow model, Sparse2Prior, first restores the artifact-corrupted FDK volume into an anatomical prior in approximately 5 s. Gaussian primitives are then initialized from this prior in a tissue-adaptive manner, which yields a compact representation with 62%-65% fewer optimized primitives than random sampling. During optimization, virtual projections synthesized at intermediate angles between the measured projections are activated in rotation, while measured projections remain dominant in the objective function. Experiments on 5, 10 and 20 measured views showed that the proposed P2-Gaussian achieved the highest PSNR and SSIM among all methods. Compared with the optimization-based Gaussian baseline, our method increases PSNR by 5.98, 4.25 and 2.49 dB and accelerates reconstruction by 2.6-3.0 times. These results indicate that coupling a learned anatomical prior with measurement-constrained Gaussian optimization is effective for sparse-view CBCT reconstruction. Code is publicly available at: https://github.com/Ballbo5354/P-2-Gaussian.
ER -