Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency
This work addresses depth estimation for robotic surgery and laparoscopic imaging, offering improved accuracy without requiring labeled data, though it is incremental as it builds on existing self-supervised methods by incorporating 3D information.
The paper tackles the problem of depth estimation in laparoscopic images, where obtaining ground truth depth data is difficult, by introducing M3Depth, a self-supervised method that leverages 3D geometric consistency from stereo pairs and outperforms previous approaches by a large margin on public and new datasets.
Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply supervised depth estimation to surgical applications. As an alternative, self-supervised methods have been introduced to train depth estimators using only synchronized stereo image pairs. However, most recent work focused on the left-right consistency in 2D and ignored valuable inherent 3D information on the object in real world coordinates, meaning that the left-right 3D geometric structural consistency is not fully utilized. To overcome this limitation, we present M3Depth, a self-supervised depth estimator to leverage 3D geometric structural information hidden in stereo pairs while keeping monocular inference. The method also removes the influence of border regions unseen in at least one of the stereo images via masking, to enhance the correspondences between left and right images in overlapping areas. Intensive experiments show that our method outperforms previous self-supervised approaches on both a public dataset and a newly acquired dataset by a large margin, indicating a good generalization across different samples and laparoscopes. Code and data are available at https://github.com/br0202/M3Depth.