Guliz Irem Gokceler

About

Guliz Irem Gokceler is a leading researcher at the intersection of computer vision, robotics, and medical imaging, with a primary focus on advancing endoscopic technologies. Her most impactful contribution is the creation of the **EndoSLAM dataset**, a comprehensive benchmark that has become a cornerstone for evaluating simultaneous localization and mapping (SLAM) and depth estimation methods in minimally invasive surgery. This work, detailed in her highly cited 2021 paper (240 citations), addresses a critical gap by providing the first dataset enabling effective quantitative benchmarking of deep learning techniques for dense topography reconstruction and pose estimation in endoscopic videos. To further push the boundaries of the field, she developed **Endo-SfMLearner**, an unsupervised monocular visual odometry and depth estimation approach that leverages this dataset. Her innovative spirit extends to creating **VR-Caps**, a virtual environment for capsule endoscopy, demonstrating her commitment to building robust simulation tools. By providing both the foundational data and novel algorithms, Gokceler’s work is instrumental in paving the way for more accurate, autonomous, and safer robotic-assisted surgeries.

Research Focus

Key Achievements

Top Papers

1. 1
   EndoSLAM dataset and an unsupervised monocular visual odometry and depth estimation approach for endoscopic videos

   240 citations · 2021
2. 2
   EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner

   5 citations · 2020
3. 3
   VR-Caps: A Virtual Environment for Capsule Endoscopy

   4 citations · 2021
4. 4
   Quantitative Evaluation of Endoscopic SLAM Methods: EndoSLAM Dataset.

   3 citations · 2020

Key Collaborators

Contact & Links