Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hein, Jonas, Calvet, Lilian, Seibold, Matthias, Tang, Siyu, Pollefeys, Marc, Fürnstahl, Philipp
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910075312930816
author Hein, Jonas
Calvet, Lilian
Seibold, Matthias
Tang, Siyu
Pollefeys, Marc
Fürnstahl, Philipp
author_facet Hein, Jonas
Calvet, Lilian
Seibold, Matthias
Tang, Siyu
Pollefeys, Marc
Fürnstahl, Philipp
contents 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 generate object mask proposals in each view and score their similarity to rendered templates using a pre-trained feature extractor. Detections are matched across views, triangulated into 3D instance candidates, and filtered using multi-view geometric consistency. Second, for pose estimation, a set of pose hypotheses is iteratively refined and scored using feature-metric scores with cross-view attention. The best hypothesis undergoes a final refinement using a novel multi-view, occlusion-aware contour registration, which minimizes reprojection errors of unoccluded contour points. Results: The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset. The method achieves millimeter-accurate pose estimates that are on par with supervised methods under controlled conditions, while maintaining full generalization to unseen instruments. These results demonstrate the feasibility of training-free, marker-less detection and tracking in surgical scenes, and highlight the unique challenges in surgical environments. Conclusion: We present a novel and flexible pipeline that effectively combines state-of-the-art foundational models, multi-view geometry, and contour-based refinement for high-accuracy 6D pose estimation of surgical instruments without task-specific training. This approach enables robust instrument tracking and scene understanding in dynamic clinical environments.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25228
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments
Hein, Jonas
Calvet, Lilian
Seibold, Matthias
Tang, Siyu
Pollefeys, Marc
Fürnstahl, Philipp
Computer Vision and Pattern Recognition
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 generate object mask proposals in each view and score their similarity to rendered templates using a pre-trained feature extractor. Detections are matched across views, triangulated into 3D instance candidates, and filtered using multi-view geometric consistency. Second, for pose estimation, a set of pose hypotheses is iteratively refined and scored using feature-metric scores with cross-view attention. The best hypothesis undergoes a final refinement using a novel multi-view, occlusion-aware contour registration, which minimizes reprojection errors of unoccluded contour points. Results: The proposed method was rigorously evaluated on real-world surgical data from the MVPSP dataset. The method achieves millimeter-accurate pose estimates that are on par with supervised methods under controlled conditions, while maintaining full generalization to unseen instruments. These results demonstrate the feasibility of training-free, marker-less detection and tracking in surgical scenes, and highlight the unique challenges in surgical environments. Conclusion: We present a novel and flexible pipeline that effectively combines state-of-the-art foundational models, multi-view geometry, and contour-based refinement for high-accuracy 6D pose estimation of surgical instruments without task-specific training. This approach enables robust instrument tracking and scene understanding in dynamic clinical environments.
title Training-free Detection and 6D Pose Estimation of Unseen Surgical Instruments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.25228