{"ID":2886926,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02408","arxiv_id":"2508.02408","title":"GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2508.02408","url_pdf":"https://arxiv.org/pdf/2508.02408v2","authors":"[\"Yikuang Yuluo\",\"Yue Ma\",\"Kuan Shen\",\"Tongtong Jin\",\"Wang Liao\",\"Yangpu Ma\",\"Fuquan Wang\"]","published":"2025-08-04T13:31:42Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[]","has_code":false}