# Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos

arXiv: https://arxiv.org/abs/2606.31007 · HTML: https://mlsanity.com/paper/2606.31007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [2017 Robotic Instrument Segmentation Challenge](https://mlsanity.com/paper/1902.06426/) (2019)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)
- [2018 Robotic Scene Segmentation Challenge](https://mlsanity.com/paper/2001.11190/) (2020)
- [CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80](https://mlsanity.com/paper/2012.12453/) (2020)
- [SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation](https://mlsanity.com/paper/2308.08746/) (2023)
- [Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark](https://mlsanity.com/paper/2109.14956/) (2021)
- [What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector](https://mlsanity.com/paper/2408.15857/) (2024)
- [SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation](https://mlsanity.com/paper/2308.07156/) (2023)
- [Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art](https://mlsanity.com/paper/2304.13014/) (2023)
- [SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking](https://mlsanity.com/paper/2502.11534/) (2025)
- [Surgical Visual Understanding (SurgVU) Dataset](https://mlsanity.com/paper/2501.09209/) (2025)
- [Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery](https://mlsanity.com/paper/2404.14040/) (2024)
- [SurgRIPE challenge: Benchmark of Surgical Robot Instrument Pose Estimation](https://mlsanity.com/paper/2501.02990/) (2025)
- [Video-based Surgical Tool-tip and Keypoint Tracking using Multi-frame Context-driven Deep Learning Models](https://mlsanity.com/paper/2501.18361/) (2025)
- [Expanded Comprehensive Robotic Cholecystectomy Dataset (CRCD)](https://mlsanity.com/paper/2412.12238/) (2024)

## Abstract (arXiv)

Vision foundation models such as SAM 3 can provide transferable object-level structure across diverse surgical video conditions, but segmentation outputs do not explicitly encode the action-conditioned semantics that define functional surgical landmarks. Estimating instrument extent and geometry differs from localizing the tip or anchor relevant to clipping, grasping, or dissecting. We investigate vision foundation model-enabled sparse action-aware landmark localization, using zero-shot, point-prompted structural masks to provide dense instrument-level context without manual pixel-level mask annotations. We propose a lightweight refinement framework that uses SAM 3 as a structural prior. A coarse multi-frame network predicts tip and anchor prompts, generating non-oracle masks that are fused with visual and heatmap features to refine functional landmark predictions. We compare direct mask-augmented supervision, prediction-derived mask-prior refinement, and auxiliary mask supervision to examine how vision foundation model-derived structure should enter a precision-oriented localization system. Experiments on 7,867 clips from 60 surgical videos spanning YouTube, Cholec80, HeiChole, SurgVU, and CRCD evaluate the approach under heterogeneous conditions. Without manual pixel-level mask annotations for training, the proposed model achieves overall F1 scores of 72.4% for tip and 58.0% for anchor localization. Ablations show that coarse-to-fine refinement provides a substantial performance gain, while prediction-derived structural priors provide additional improvement when incorporated as intermediate guidance rather than direct localization targets.