SAMSNeRF: Segment Anything Model (SAM) Guides Dynamic Surgical Scene Reconstruction by Neural Radiance Field (NeRF)
This work addresses the need for accurate 3D surgical scene reconstruction to enhance intraoperative navigation and automation for surgeons, representing an incremental improvement by integrating existing models.
The paper tackles the problem of reconstructing dynamic surgical scenes from videos, which is challenging due to moving tools, by proposing SAMSNeRF, a method that combines SAM and NeRF to generate accurate 3D positions of surgical tools, resulting in high-fidelity reconstructions as demonstrated on public endoscopy videos.
The accurate reconstruction of surgical scenes from surgical videos is critical for various applications, including intraoperative navigation and image-guided robotic surgery automation. However, previous approaches, mainly relying on depth estimation, have limited effectiveness in reconstructing surgical scenes with moving surgical tools. To address this limitation and provide accurate 3D position prediction for surgical tools in all frames, we propose a novel approach called SAMSNeRF that combines Segment Anything Model (SAM) and Neural Radiance Field (NeRF) techniques. Our approach generates accurate segmentation masks of surgical tools using SAM, which guides the refinement of the dynamic surgical scene reconstruction by NeRF. Our experimental results on public endoscopy surgical videos demonstrate that our approach successfully reconstructs high-fidelity dynamic surgical scenes and accurately reflects the spatial information of surgical tools. Our proposed approach can significantly enhance surgical navigation and automation by providing surgeons with accurate 3D position information of surgical tools during surgery.The source code will be released soon.