Jason Rambach

German Research Centre for Artificial Intelligence

Papers

Total Citations

191

H-Index

About

Jason Rambach is a leading researcher at the intersection of computer vision, augmented reality, and robotics, with a primary focus on 6DoF (six degrees of freedom) object pose estimation. His work is pivotal for enabling precise interaction between digital and physical worlds, particularly in Industry 4.0 and augmented reality assembly scenarios. Rambach’s major contributions center on developing deep neural network approaches that can accurately estimate an object’s position and orientation from single images, even when objects have multiple removable or adjustable parts—a problem known as multi-state object pose estimation. His most cited paper, “Deep Multi-state Object Pose Estimation for Augmented Reality Assembly” (2019, 100 citations), demonstrates this capability for complex assembly tasks. He has also pioneered the use of synthetic training data to overcome the scarcity of real annotated images, as seen in “SynPo-Net” (2021, 19 citations) and his work on learning from synthetic single-channel images (2018, 32 citations). With over 190 total citations, Rambach’s research is instrumental in advancing human-robot collaboration and intelligent manufacturing, making him a key figure in applied visual computing for Industry 4.0.