Eric Turner
Papers
1
Total Citations
14
H-Index
1
About
Eric Turner is a researcher in computer vision and robotics, specializing in visual-inertial odometry and 3D scene understanding. His work focuses on integrating learned priors with classical geometric methods to improve the robustness and accuracy of autonomous systems. Turner’s most notable contribution, "Learned Monocular Depth Priors in Visual-Inertial Initialization" (2022), has garnered 14 citations and addresses a critical challenge in visual-inertial systems: reliable initialization in texture-poor or dynamic environments. By leveraging deep learning to predict depth from a single image, his approach enhances the convergence and stability of state estimation pipelines, enabling more resilient performance in real-world applications like drones and augmented reality. Turner’s research bridges the gap between data-driven perception and traditional sensor fusion, offering practical solutions for systems that must operate without prior scene knowledge. His work is particularly impactful for students and engineers seeking to understand how modern machine learning can augment classical robotics algorithms, making autonomous navigation more accessible and dependable.
Research Focus
Key Achievements
Top Papers
- 1Learned Monocular Depth Priors in Visual-Inertial Initialization14 citations · 2022