SENDD: Sparse Efficient Neural Depth and Deformation for Tissue Tracking
This enables real-time 3D tissue tracking for surgical automation, though it builds incrementally on existing 2D tracking methods.
The paper tackles 3D tissue motion tracking for robot-assisted surgery by extending prior 2D tracking to estimate 3D flow and depth using sparse keypoints, achieving comparable performance to 2D models while enabling 3D applications at 10fps with under 500,000 parameters.
Deformable tracking and real-time estimation of 3D tissue motion is essential to enable automation and image guidance applications in robotically assisted surgery. Our model, Sparse Efficient Neural Depth and Deformation (SENDD), extends prior 2D tracking work to estimate flow in 3D space. SENDD introduces novel contributions of learned detection, and sparse per-point depth and 3D flow estimation, all with less than half a million parameters. SENDD does this by using graph neural networks of sparse keypoint matches to estimate both depth and 3D flow anywhere. We quantify and benchmark SENDD on a comprehensively labelled tissue dataset, and compare it to an equivalent 2D flow model. SENDD performs comparably while enabling applications that 2D flow cannot. SENDD can track points and estimate depth at 10fps on an NVIDIA RTX 4000 for 1280 tracked (query) points and its cost scales linearly with an increasing/decreasing number of points. SENDD enables multiple downstream applications that require estimation of 3D motion in stereo endoscopy.