GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuluo, Yikuang, Ma, Yue, Shen, Kuan, Jin, Tongtong, Liao, Wang, Ma, Yangpu, Wang, Fuquan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480061833216
author Yuluo, Yikuang
Ma, Yue
Shen, Kuan
Jin, Tongtong
Liao, Wang
Ma, Yangpu
Wang, Fuquan
author_facet Yuluo, Yikuang
Ma, Yue
Shen, Kuan
Jin, Tongtong
Liao, Wang
Ma, Yangpu
Wang, Fuquan
contents 3D Gaussian Splatting (3DGS) has emerged as a promising approach for CT reconstruction. However, existing methods rely on the average gradient magnitude of points within the view, often leading to severe needle-like artifacts under sparse-view conditions. To address this challenge, we propose GR-Gaussian, a graph-based 3D Gaussian Splatting framework that suppresses needle-like artifacts and improves reconstruction accuracy under sparse-view conditions. Our framework introduces two key innovations: (1) a Denoised Point Cloud Initialization Strategy that reduces initialization errors and accelerates convergence; and (2) a Pixel-Graph-Aware Gradient Strategy that refines gradient computation using graph-based density differences, improving splitting accuracy and density representation. Experiments on X-3D and real-world datasets validate the effectiveness of GR-Gaussian, achieving PSNR improvements of 0.67 dB and 0.92 dB, and SSIM gains of 0.011 and 0.021. These results highlight the applicability of GR-Gaussian for accurate CT reconstruction under challenging sparse-view conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
Yuluo, Yikuang
Ma, Yue
Shen, Kuan
Jin, Tongtong
Liao, Wang
Ma, Yangpu
Wang, Fuquan
Image and Video Processing
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has emerged as a promising approach for CT reconstruction. However, existing methods rely on the average gradient magnitude of points within the view, often leading to severe needle-like artifacts under sparse-view conditions. To address this challenge, we propose GR-Gaussian, a graph-based 3D Gaussian Splatting framework that suppresses needle-like artifacts and improves reconstruction accuracy under sparse-view conditions. Our framework introduces two key innovations: (1) a Denoised Point Cloud Initialization Strategy that reduces initialization errors and accelerates convergence; and (2) a Pixel-Graph-Aware Gradient Strategy that refines gradient computation using graph-based density differences, improving splitting accuracy and density representation. Experiments on X-3D and real-world datasets validate the effectiveness of GR-Gaussian, achieving PSNR improvements of 0.67 dB and 0.92 dB, and SSIM gains of 0.011 and 0.021. These results highlight the applicability of GR-Gaussian for accurate CT reconstruction under challenging sparse-view conditions.
title GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.02408