Michael Giering

About

Michael Giering’s research bridges computer vision and materials science through the innovative application of deep learning. His primary contributions lie in automated occlusion edge detection for RGB-D frames—a critical capability for mobile robotics and scene understanding—and in using deep neural networks to tailor structural material properties. Giering’s work on occlusion edge detection, published in 2014 and 2016, developed convolutional network architectures that extract range discontinuities directly from images and video, a task previously reliant on expensive range sensors. These papers have accumulated 26 and 9 citations respectively, establishing foundational methods for vision-based robotic perception. His 2019 paper on material property tailoring, with 11 citations, extends deep learning into materials engineering, demonstrating how neural networks can optimize structural designs for advanced manufacturing. This cross-disciplinary approach—applying AI to both perceptual and physical domains—showcases Giering’s versatility. His research is particularly notable for addressing practical automation challenges, from enabling robots to navigate cluttered environments to accelerating the discovery of novel materials. For students and researchers, Giering’s work exemplifies how deep learning can solve diverse, real-world problems at the intersection of robotics, vision, and materials science.

Research Focus

Key Achievements

Top Papers

1. 1
   Deep Learning for Automated Occlusion Edge Detection in RGB-D Frames

   26 citations · 2016
2. 2
   Structural Material Property Tailoring Using Deep Neural Networks

   11 citations · 2019
3. 3
   Occlusion Edge Detection in RGB-D Frames using Deep Convolutional Networks

   9 citations · 2014

Key Collaborators

Contact & Links