EndoSurf：基于立体内窥镜视频的可变形组织神经表面重建
EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
AI总结：
针对内窥镜视频软组织重建难题，EndoSurf提出三神经场表示，结合变形场与SDF/辐射场，通过正则化解耦几何外观，显著提升高保真形状重建质量。
摘要：
从立体内窥镜视频中重建软组织是许多医学应用的基本前提。以往的方法由于对三维场景的表征不足，难以生成高质量的几何形状和外观。为解决这一问题，我们提出了一种新颖的基于神经场的方法，称为EndoSurf，它能有效地从RGBD序列中学习表示变形的表面。在EndoSurf中，我们使用三个神经场分别建模表面动态、形状和纹理。首先，利用变形场将三维点从观测空间变换到规范空间。然后，符号距离函数（SDF）场和辐射场分别预测它们的SDF和颜色，从而可以通过可微体积渲染合成RGBD图像。我们通过定制多种正则化策略并解耦几何与外观来约束学习到的形状。在公开内窥镜数据集上的实验表明，EndoSurf显著优于现有解决方案，特别是在重建高保真形状方面。代码可在https://github.com/Ruyi-Zha/endosurf.git获取。
英文摘要：
Reconstructing soft tissues from stereo endoscope videos is an essential prerequisite for many medical applications. Previous methods struggle to produce high-quality geometry and appearance due to their inadequate representations of 3D scenes. To address this issue, we propose a novel neural-field-based method, called EndoSurf, which effectively learns to represent a deforming surface from an RGBD sequence. In EndoSurf, we model surface dynamics, shape, and texture with three neural fields. First, 3D points are transformed from the observed space to the canonical space using the deformation field. The signed distance function (SDF) field and radiance field then predict their SDFs and colors, respectively, with which RGBD images can be synthesized via differentiable volume rendering. We constrain the learned shape by tailoring multiple regularization strategies and disentangling geometry and appearance. Experiments on public endoscope datasets demonstrate that EndoSurf significantly outperforms existing solutions, particularly in reconstructing high-fidelity shapes. Code is available at https://github.com/Ruyi-Zha/endosurf.git.
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。
