EndoGaussians：面向可变形内窥组织重建的单视图动态高斯泼溅
EndoGaussians: Single View Dynamic Gaussian Splatting for Deformable Endoscopic Tissues Reconstruction
AI总结：
本文提出EndoGaussians，首次将高斯泼溅用于动态内窥镜三维重建，克服NeRF方法局限，在多个内窥镜数据集上取得最先进性能。
摘要：
从内窥镜视频中对可变形软体组织进行精确的三维重建，是虚拟现实手术和医学图像分析等医学应用中的关键挑战。现有方法在精度和幻觉组织部分的模糊性方面往往存在不足，限制了其实用价值。在本工作中，我们提出了EndoGaussians，这是一种利用高斯泼溅进行动态内窥镜三维重建的新方法。该方法首次将高斯泼溅应用于该领域，克服了以往基于NeRF技术的局限性。在各种内窥镜数据集上的定量评估表明，我们的方法树立了新的最先进标准。这些进展使我们的方法成为医学专业人员的一种有前景的工具，为医学领域的实际应用提供了更可靠、更高效的三维重建。
英文摘要：
The accurate 3D reconstruction of deformable soft body tissues from endoscopic videos is a pivotal challenge in medical applications such as VR surgery and medical image analysis. Existing methods often struggle with accuracy and the ambiguity of hallucinated tissue parts, limiting their practical utility. In this work, we introduce EndoGaussians, a novel approach that employs Gaussian Splatting for dynamic endoscopic 3D reconstruction. This method marks the first use of Gaussian Splatting in this context, overcoming the limitations of previous NeRF-based techniques. Our method sets new state-of-the-art standards, as demonstrated by quantitative assessments on various endoscope datasets. These advancements make our method a promising tool for medical professionals, offering more reliable and efficient 3D reconstructions for practical applications in the medical field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
