研究人员开发了Ultra-Wide-NeRF，一种用于重建宽视场3D超声图像的新方法。该方法利用神经辐射场框架内的多变量3D高斯模型，精确模拟凸探头发出的发散声束。通过显式考虑声束几何形状和随深度的分辨率变化，Ultra-Wide-NeRF显著减少了伪影和混叠，为高保真新视角合成提供了连续的神经表示。该方法已在腔内超声心动图的模体和猪数据集上得到验证，增强了术中导航的空间背景。 AI
影响 提高了3D超声重建的准确性和可视化效果，可能有助于手术导航和分割任务。
排序理由 学术论文，详细介绍了一种新的3D超声重建方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Wide Field-of-View (WFoV) reconstruction enhances 3D ultrasound imaging by providing valuable anatomical context for segmentation models and visualization. Clinical ultrasound volumes are predominantly acquired using convex probes, which generate expanding, diverging acoustic bea…
arXiv:2604.24187v1 Announce Type: new Abstract: Wide Field-of-View (WFoV) reconstruction enhances 3D ultrasound imaging by providing valuable anatomical context for segmentation models and visualization. Clinical ultrasound volumes are predominantly acquired using convex probes, …
Wide Field-of-View (WFoV) reconstruction enhances 3D ultrasound imaging by providing valuable anatomical context for segmentation models and visualization. Clinical ultrasound volumes are predominantly acquired using convex probes, which generate expanding, diverging acoustic bea…