Surgical 3D reconstruction is a critical area of research in robotic surgery, with recent works adopting variants of dynamic radiance fields to achieve success in 3D reconstruction of deformable tissues from single-viewpoint videos. However, these methods often suffer from time-consuming optimization or inferior quality, limiting their adoption in downstream tasks. Inspired by 3D Gaussian Splatting, a recent trending 3D representation, we present EndoGS, applying Gaussian Splatting for deformable endoscopic tissue reconstruction. Specifically, our approach incorporates deformation fields to handle dynamic scenes, depth-guided supervision to optimize 3D targets with a single viewpoint, and a spatial-temporal weight mask to mitigate tool occlusion. As a result, EndoGS reconstructs and renders high-quality deformable endoscopic tissues from a single-viewpoint video, estimated depth maps, and labeled tool masks. Experiments on DaVinci robotic surgery videos demonstrate that EndoGS achieves superior rendering quality. Code is available at https://github.com/HKU-MedAI/EndoGS.

翻译：手术三维重建是机器人手术中的关键研究方向，近期研究采用动态辐射场变体方法，实现了从单视角视频中对可变形组织进行三维重建。然而，这类方法常面临优化耗时长或重建质量欠佳的问题，限制了其在后续任务中的应用。受新兴三维表示方法——高斯泼溅的启发，我们提出EndoGS，将高斯泼溅用于可变形内镜组织重建。具体而言，我们的方法融合形变场处理动态场景、深度引导监督实现单视角三维目标优化，并采用时空权重掩码缓解器械遮挡问题。实验表明，EndoGS能从单视角视频、估计深度图和标注器械掩码中，高质量重建并渲染可变形内镜组织。在达芬奇机器人手术视频上的实验证实，EndoGS具有卓越的渲染质量。代码已开源至https://github.com/HKU-MedAI/EndoGS。