Training-free 6D pose estimation for unseen surgical instruments using only a CAD model as prior knowledge.
March 27, 2026
Original Paper
Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments
arXiv · 2603.25228
The Takeaway
This removes the need for expensive, manual annotation of surgical tool data. The method achieves millimeter-level accuracy and generalizes immediately to new tools, solving a major bottleneck in medical robotics and computer-assisted intervention.
From the abstract
Purpose: Accurate detection and 6D pose estimation of surgical instruments are crucial for many computer-assisted interventions. However, supervised methods lack flexibility for new or unseen tools and require extensive annotated data. This work introduces a training-free pipeline for accurate multi-view 6D pose estimation of unseen surgical instruments, which only requires a textured CAD model as prior knowledge. Methods: Our pipeline consists of two main stages. First, for detection, we genera