Marc Niethammer

University of North Carolina at Chapel Hill

Papers

Total Citations

131

H-Index

About

Marc Niethammer is a leading researcher in robotics and computer vision, with key contributions in motion planning, 3D reconstruction, and medical imaging. His work on "LQG-Obstacles" (87 citations) pioneered a novel framework integrating linear-quadratic Gaussian control with collision avoidance, enabling safe robot navigation under motion and sensing uncertainty—a foundational advance for autonomous systems. In shape analysis, his "Accurate Point Cloud Registration with Robust Optimal Transport" (26 citations) demonstrated how modern optimal transport solvers significantly boost registration accuracy for both optimization and deep learning methods, setting new benchmarks in 3D matching. More recently, Niethammer has pushed boundaries in multi-modal perception with "Joint Depth Prediction and Semantic Segmentation with Multi-View SAM" (10 citations), which leverages multiple camera views to overcome monocular limitations, and "Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos" (8 citations), addressing the challenging domain of surgical imaging. His research consistently bridges theoretical rigor with practical robotics applications, earning him recognition as a pioneer in feedback control under uncertainty and a driving force in advancing 3D vision for real-world systems.