English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The accurate reconstruction of surgical scenes from surgical videos iscritical for various applications, including intraoperative navigation andimage-guided robotic surgery automation. However, previous approaches, mainlyrelying on depth estimation, have limited effectiveness in reconstructingsurgical scenes with moving surgical tools. To address this limitation andprovide accurate 3D position prediction for surgical tools in all frames, wepropose a novel approach called SAMSNeRF that combines Segment Anything Model(SAM) and Neural Radiance Field (NeRF) techniques. Our approach generatesaccurate segmentation masks of surgical tools using SAM, which guides therefinement of the dynamic surgical scene reconstruction by NeRF. Ourexperimental results on public endoscopy surgical videos demonstrate that ourapproach successfully reconstructs high-fidelity dynamic surgical scenes andaccurately reflects the spatial information of surgical tools. Our proposedapproach can significantly enhance surgical navigation and automation byproviding surgeons with accurate 3D position information of surgical toolsduring surgery.The source code will be released soon.

SAMSNeRF: Segment Anything Model (SAM) Guides Dynamic Surgical Scene Reconstruction by Neural Radiance Field (NeRF)