Surgical Perception

3D scene reconstruction and tracking play an important role in achieving autonomous surgery, providing crucial information for scene understanding, path planning, and navigation. This task is very challenging due to the need to handle unstructured, dynamic, and deformable surgical scenes with texture-less and moist tissues and instruments.


BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction Using Neural Radiance Fields

WACV 2025


SuPerPM: A Surgical Perception Framework Based on Deep Point Matching Learned from Physical Constrained Simulation Data

IROS 2024


BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives

CVPR Workshop 2024


ORRN: An ODE-Based Recursive Registration Network for Deformable Respiratory Motion Estimation with Lung 4DCT Images

IEEE Transactions on Biomedical Engineering 2023


Semantic-Super: A Semantic-Aware Surgical Perception Framework for Endoscopic Tissue Identification, Reconstruction, and Tracking

ICRA 2023


Don't Get Burned: Thermal Monitoring of Vessel Sealing Using a Miniature Infrared Camera

SPIE 2017