EndoGaussians: Single View Dynamic Gaussian Splatting for Deformable Endoscopic Tissues Reconstruction
This addresses a pivotal challenge for medical applications like VR surgery and medical image analysis, though it appears incremental as it adapts an existing technique to a new domain.
The paper tackles 3D reconstruction of deformable soft body tissues from endoscopic videos, introducing EndoGaussians which uses Gaussian Splatting to achieve state-of-the-art accuracy on various datasets.
The accurate 3D reconstruction of deformable soft body tissues from endoscopic videos is a pivotal challenge in medical applications such as VR surgery and medical image analysis. Existing methods often struggle with accuracy and the ambiguity of hallucinated tissue parts, limiting their practical utility. In this work, we introduce EndoGaussians, a novel approach that employs Gaussian Splatting for dynamic endoscopic 3D reconstruction. This method marks the first use of Gaussian Splatting in this context, overcoming the limitations of previous NeRF-based techniques. Our method sets new state-of-the-art standards, as demonstrated by quantitative assessments on various endoscope datasets. These advancements make our method a promising tool for medical professionals, offering more reliable and efficient 3D reconstructions for practical applications in the medical field.