Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video
This addresses the challenge of accurate 3D reconstruction in medical endoscopy for clinicians, offering a self-supervised approach that eliminates the need for patient-specific data or manual annotation.
The paper tackles the problem of dense 3D reconstruction from monocular endoscopic videos without prior anatomical models or manual input, achieving submillimeter mean residual errors in a cross-patient study using CT scans as ground truth.
We present a self-supervised learning-based pipeline for dense 3D reconstruction from full-length monocular endoscopic videos without a priori modeling of anatomy or shading. Our method only relies on unlabeled monocular endoscopic videos and conventional multi-view stereo algorithms, and requires neither manual interaction nor patient CT in both training and application phases. In a cross-patient study using CT scans as groundtruth, we show that our method is able to produce photo-realistic dense 3D reconstructions with submillimeter mean residual errors from endoscopic videos from unseen patients and scopes.