Monocular Endoscopic

Monocular endoscopic image analysis focuses on extracting three-dimensional information and other relevant data from single-camera endoscopic videos, overcoming the limitations of traditional stereo methods. Current research heavily utilizes deep learning architectures, including convolutional neural networks (CNNs), transformers, and neural radiance fields (NeRFs), often combined with geometric modeling and techniques like structure-from-motion (SfM) to achieve accurate depth estimation and 3D reconstruction. This work is crucial for improving minimally invasive surgical procedures by enabling better intraoperative visualization, navigation, and quantitative analysis of anatomical structures, ultimately enhancing surgical precision and patient outcomes. The development of robust and efficient methods for monocular endoscopic analysis is driving advancements in computer-aided diagnosis and robotic surgery.