发表机构
Guangxi University; Guangxi Medical University Cancer Hospital; Shanghai University（广西大学; 广西医科大学附属肿瘤医院; 上海大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对稀疏视角X射线成像中的结构模糊与噪声问题，提出LINGO框架，结合潜在掩膜初始化与动态梯度优化，加速训练并提升新视角合成与CT重建质量。
AI 中文摘要
在稀疏视角X射线成像的新视角合成和计算机断层扫描（CT）重建中，角度覆盖不足会导致结构模糊和噪声累积。将3D高斯泼溅（3DGS）与X射线吸收物理相结合可以获得有前景的结果，但该方法存在初始化噪声大、位置不敏感以及低密度区域梯度弱的问题。本文提出了一种统一的潜在初始化与梯度优化（LINGO）框架来解决这些问题。LINGO将潜在掩膜空间初始化与动态梯度优化相结合，以提高点云结构的完整性，同时加速训练。它利用X射线掩膜构建体素级3D滤波器，以稳健地抑制背景噪声并提供可靠的几何先验。通过采用自适应体素缩放策略和动态缩放损失，LINGO能够调整空间分辨率并显式放大低密度结构中的梯度。为了评估初始化质量，我们引入了初始化点云结构偏差（IPSD）指标。在X3D数据集上的实验表明，对于新视角合成任务，在相同的稀疏视角设置下，与基线相比，LINGO将峰值信噪比（PSNR）和结构相似性指数（SSIM）平均提高了0.72和0.0039，在5k步内达到了通常需要30k次迭代训练的最先进模型相当的重建质量。对于CT重建任务，LINGO也表现出一致的改进，平均PSNR和SSIM增益分别为0.36和0.0134。这些结果凸显了LINGO在不同稀疏视角成像场景中加速训练和提升重建质量方面的有效性。
英文摘要
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.
