Purpose: Accurate 6 DoF pose estimation of surgical tools is critical for automa- tion, robotic proprioception, and safe interaction with the tissue operated on. Kinematics-based approaches suffer from accumulated errors due to the cable- driven nature of robotic arms, while vision-based methods often rely on external markers or trackers. Although more recent vision-based advances have been pro- posed, these two-stage pose estimation methods often lack real-time robustness due to accumulated errors and computational overhead. Methods: We propose a novel end-to-end trainable model, PICO. Our model employs a multi-task learning architecture to predict segmentation and depth maps, alongside regression of translation and rotation parameters. We define two proxy tasks that enforce geometric consistency in both 2D and 3D spaces, improving accuracy and robustness. For this, we propose a projection loss, and a point-to-point loss. Results: We evaluate our method on the SurgRIPE dataset, benchmarking its performance against state-of-the-art approaches using standard 6DoF pose esti- mation metrics. Our results demonstrate consistently strong performance across all four subsets, specifically in rotation, ranking second even under occlusion. It also demonstrates comparable translational performance, remaining competitive, especially in occluded cases. Conclusion: PICO demonstrates the effectiveness of multi-task learning and geometry-aware proxy tasks for robust and reliable surgical tool pose estimation, especially in occluded scenarios, highlighting potential for future applications.
Figures & tables
Figure 1: Proposed training framework Given an input RGB image, the tool is first cropped, resized and fed into a U-Net style architecture with a ResNet-50 encoder backbone. The learned features are fed into a decoder and subsequently pass through separate depth and segmentation heads. Simultaneously, the encoder features are passed through linear layers and regression heads for pose estimation. The estimated pose is used to transform the 3D tool model, and both the 2D projection and 3D representation of the tool are minimised through two defined proxy tasks. All losses are optimized jointly with the multi task loss function.
Table 1: Table showing comparison of different model performances in EndoVis SurgRIPE challenge across LND, LND occluded, MBF, and MBF occluded datasets. The results of the best-performing model are highlighted in bold, while the second-best model results are underlined, for each type of error. The top five rows show performance for multi-stage methods, while the bottom two rows demonstrate the single-stage methods.
Table 2: Table showing ablation studies for multi-task loss function and impact of of auxiliary tasks on model performance, evaluated across EndoVis SurgRIPE challenge LND, LND occluded, MBF, and MBF occluded datasets.
Figure 2: Relationship between xy and z translation errors and ADD distances for the four datasets. Each plot contains both xy (red) and z (blue) translation error measurements plotted against ADD distance. The dashed line represents x=y , indicating where the translation error and ADD distance are equal.
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.
Daiyun Shen, Shuojue Yang, Chang Han Low +4
National University of Singapore, Singapore · The Chinese University of Hong Kong, HKSAR, China
Accurate 6-DoF object pose estimation is fundamental to robotic manipulation, yet vision-based methods often fail under occlusion, poor lighting, and reflective or transparent surfaces. We present YOTO, a tactile-only pose estimation system that recovers the full 6-DoF object pose from a single pair of simultaneous contacts, without requiring contact history. YOTO represents each tactile contact as a local 3D point cloud and localizes it on the object surface through a coarse-to-fine network. The two localized contacts, together with the calibrated sensor poses, are then fed to a closed-form normal-aware SVD solver that recovers the full 6-DoF object pose in one step. To reduce real-data requirements, the localization network is pretrained on virtual tactile patches sampled from the object model and fine-tuned with a small number of real contacts. We further show that YOTO can operate on object models reconstructed from consumer-grade mobile scans, and quantify the gap relative to CAD-based models. Experiments on four geometrically diverse objects demonstrate accurate tactile contact localization and pose estimation, outperforming vision-based and geometric baselines, especially when visual perception is unreliable. Code, trained models, and the real GelSight dataset will be released upon publication.
Pengfei Ye, Yuxiang Ma, Haonan Chen +5
MIT CSAIL · Harvard University · University of Cambridge
We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision transformer as its only pretrained component within the pose estimation pipeline, B2TFPose extracts dense patch-level features that generalize across the synthetic-to-real domain gap without any task-specific fine-tuning, revisiting the classical local feature matching paradigm through the lens of large-scale self-supervised foundation models. Three contributions advance the training-free state of the art. A geodesic non-maximum suppression strategy retrieves a viewpoint-diverse template set for coarse-to-fine correspondence matching. Render-guided Re-Correspondence (RRC) synthesizes object-specific views at the estimated pose and re-establishes dense 2D-3D correspondences to sharpen the initial estimate without additional learned parameters. A multi-mask hypothesis selection strategy jointly scores competing segmentation candidates to resolve segmentation ambiguity. On the seven core datasets of the BOP Benchmark, B2TFPose achieves 40.7 mean AR without refinement and 56.4 with refinement, establishing state-of-the-art performance among training-free RGB methods and outperforming trained counterparts including GigaPose and GenFlow, at competitive inference speed.
Ali Rafiaei, Michael Greenspan
Dept. Electrical & Computer Engineering, Ingenuity Labs Queen’s University Kingston, ON, Canada