SurfSurg6D: Geometry Consistent Dense Correspondence for Textureless Surgical Instrument Pose Estimation
For the surgical robotics community, this work provides a tailored solution to a known bottleneck (textureless instrument pose estimation) with improved performance, though it is an incremental step combining dataset generation and a dense-correspondence framework.
The paper addresses the challenge of 6D pose estimation for textureless surgical instruments by introducing a new dataset (SynSurg6D) and a dense-correspondence framework (SurfSurg6D). The method outperforms existing approaches on multiple benchmarks, achieving robust RGB-only pose estimation.
Surgical instrument pose estimation provides crucial information for promising applications, including autonomous robotic surgery, skill assessment, and standardization of surgical workflow. However, this task remains highly challenging due to high precision requirements, frequent occlusions, textureless instruments, scarcity of depth information and very limited annotated data. These constraints often lead to unsatisfactory performance when employing general object pose estimation approaches to surgical scenarios. To address these issues, we first construct a new dataset SynSurg6D, to alleviate the data shortage in this task. We further propose SurfSurg6D, a dense-correspondence framework tailored for surgical instrument pose estimation. Experimental results on the SurgRIPE, EndoVis2018 and SurgPose datasets demonstrate that the introduction of our generated dataset SynSurg6D is able to diversify the pose distributions, thus enhancing the performance of existing approaches. Furthermore, SurfSurg6D outperforms existing methods, providing a robust solution for precise and efficient RGB-only pose estimation.