Problem
Research questions and friction points this paper is trying to address.
sparse-view X-ray imaging
novel view synthesis
CT reconstruction
structural ambiguity
accumulated noise
LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting
🤖 AI Summary
为解决稀疏视角X射线成像中的结构模糊和噪声累积问题，提出LINGO框架，结合潜在初始化与梯度优化，提升点云结构完整性和训练速度。
📝 Abstract
In novel view synthesis and Computed Tomography (CT) reconstruction with sparse-view X-ray imaging, insufficient angular coverage leads to structural ambiguity and accumulated noise. Integrating 3D Gaussian Splatting (3DGS) with X-ray absorption physics can achieve promising results, but it suffers from noisy initialization, positional insensitivity, and weak gradients in low-density regions. In this paper, we propose a unified Latent Initialization and Gradient Optimization (LINGO) framework to address these issues. LINGO combines latent mask-space initialization with dynamic gradient optimization to improve point cloud structural completeness while accelerating training. It constructs voxel-level 3D filters from X-ray masks to robustly suppress background noise and provide reliable geometric priors. By employing an adaptive voxel scaling strategy and dynamically scaling loss, LINGO can adjust spatial resolution and explicitly amplify gradients in low-density structures. To evaluate the quality of initialization, we introduce the Initialization Point Cloud Structural Deviation (IPSD) metric. Experiments on the X3D dataset indicate that for the novel view synthesis task, LINGO improves the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) by an average of 0.72 and 0.0039, respectively, over baselines under identical sparse-view settings, achieving comparable reconstruction quality within 5k steps to state-of-the-art models typically trained with 30k iterations. For the CT reconstruction task, LINGO also demonstrates consistent improvements, with average PSNR and SSIM gains of 0.36 and 0.0134. These results highlight LINGO's effectiveness in both accelerating training and enhancing reconstruction quality across different sparse-view imaging scenarios.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Latent Initialization
Gradient Optimization
3D Gaussian Splatting
Sparse-view X-ray
Adaptive Voxel Scaling
🔎 Similar Papers
No similar papers found.
