Sparse-Point Initialization and Decaying Opacity Perturbation for Sparse-View CT Reconstruction with 3D Gaussian Splatting
Authors:
- Ying ChenYCYing Chen
- Yongning ZouYZYongning Zou
- Kuan ShenKSKuan Shen
- Yikuang YuluoYYYikuang Yuluo
- Guowei ZhongGZGuowei Zhong
- Yu PengYPYu Peng
Preprint
- 5 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Sparse-view computed tomography (CT) reduces radiation dose and acquisition time, but the limited number of projections makes the reconstruction problem highly underdetermined, leading to streak artifacts and structural degradation. Existing 3D Gaussian Splatting (3DGS)-based CT reconstruction methods typically initialize Gaussian primitives from full FDK point clouds, causing streak artifacts and beam-hardening responses in sparse-view FDK reconstructions to be inherited by the initial Gaussian distribution. Moreover, limited projection supervision tends to drive Gaussian primitives into fixed co-adaptation relationships, resulting in needle-like artifacts during optimization. To address these issues, we propose a sparse-view CT reconstruction method that combines Sparse-Point Initialization (SPI) with Decaying Opacity Perturbation (DOP). SPI selects representative structural points from the FDK reconstruction through joint density-gradient scoring and improves spatial coverage using Adaptive Boundary Expansion (ABE), thereby reducing artifact contamination in the initial Gaussian distribution. DOP applies iteration-decaying multiplicative Laplace noise to Gaussian opacities during training, continuously modulating Gaussian contributions to suppress fixed co-adaptation. Experiments on the public FIPS dataset and self-built industrial CT datasets demonstrate that the proposed method improves PSNR by up to 1.132~dB and SSIM by up to 0.023 over the R2-Gaussian baseline under 25-view reconstruction, while effectively reducing the Co-Adaptation Score (CA).Keywords
This publication has 17 references indexed in Scilit:
- Image fast reconstruction for sparse view computed tomography with reduced sampling integration timeDisplays, 2024
- Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CTIEEE Transactions on Medical Imaging, 2018
- LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CTIEEE Transactions on Medical Imaging, 2018
- Deep Convolutional Neural Network for Inverse Problems in ImagingIEEE Transactions on Image Processing, 2017
- Sparse-view x-ray CT reconstruction via total generalized variation regularizationPhysics in Medicine & Biology, 2014
- Industrial applications of computed tomographyCIRP Annals, 2014
- Computed tomography for dimensional metrologyCIRP Annals, 2011
- Compressed sensing based cone‐beam computed tomography reconstruction with a first‐order methoda)Medical Physics, 2010
- Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimizationPhysics in Medicine & Biology, 2008
- Prior image constrained compressed sensing (PICCS): A method to accurately reconstruct dynamic CT images from highly undersampled projection data setsMedical Physics, 2008