Surgical Neural Radiance Fields from One Image
Journal:
arXiv
Published Date:
Jul 1, 2025
Abstract
Purpose: Neural Radiance Fields (NeRF) offer exceptional capabilities for 3D
reconstruction and view synthesis, yet their reliance on extensive multi-view
data limits their application in surgical intraoperative settings where only
limited data is available. In particular, collecting such extensive data
intraoperatively is impractical due to time constraints. This work addresses
this challenge by leveraging a single intraoperative image and preoperative
data to train NeRF efficiently for surgical scenarios.
Methods: We leverage preoperative MRI data to define the set of camera
viewpoints and images needed for robust and unobstructed training.
Intraoperatively, the appearance of the surgical image is transferred to the
pre-constructed training set through neural style transfer, specifically
combining WTC2 and STROTSS to prevent over-stylization. This process enables
the creation of a dataset for instant and fast single-image NeRF training.
Results: The method is evaluated with four clinical neurosurgical cases.
Quantitative comparisons to NeRF models trained on real surgical microscope
images demonstrate strong synthesis agreement, with similarity metrics
indicating high reconstruction fidelity and stylistic alignment. When compared
with ground truth, our method demonstrates high structural similarity,
confirming good reconstruction quality and texture preservation.
Conclusion: Our approach demonstrates the feasibility of single-image NeRF
training in surgical settings, overcoming the limitations of traditional
multi-view methods.
