Manuel Nickel

Papers

Total Citations

H-Index

About

Manuel Nickel is a leading researcher in computer vision and robotics, whose work focuses on enabling machines to perceive and interact with the world in three dimensions. His primary research areas include 6D pose estimation, 3D shape reconstruction, and self-supervised learning from monocular images. Nickel’s major contributions lie in tackling the critical challenge of scaling object-level perception from a few instances to hundreds of classes—a prerequisite for robots operating in unstructured, real-world environments. His pioneering work, "CPS: Class-level 6D Pose and Shape Estimation From Monocular Images" (2020), introduced the first deep learning approach capable of jointly estimating both the 6D pose and 3D shape of multiple object categories from a single image. Building on this, his follow-up work, "CPS++" (2020), leveraged self-supervised learning to significantly improve accuracy and robustness, achieving 35 citations. These contributions have laid the groundwork for more scalable and practical robotic systems, enabling applications from warehouse automation to household assistance. Nickel’s research is essential reading for anyone interested in bridging the gap between controlled lab settings and the messy, object-rich reality of everyday life.