Denis Fadeyev
Papers
2
Total Citations
20
H-Index
2
About
Denis Fadeyev is a researcher at the intersection of computer vision and robotics, with a focus on enabling machines to perceive and interact with complex physical environments. His work centers on two key challenges: robust object recognition and real-time pose estimation, particularly in cluttered or unconventional robotic systems. In his highly cited 2019 paper on deep learning-based object recognition, Fadeyev demonstrated that physically-realistic synthetic depth scenes can effectively train neural networks to recognize objects and estimate their 3D poses—a critical capability for robotic grasping and manipulation. This work, which has garnered 11 citations, addresses the practical difficulty of acquiring large annotated real-world datasets by leveraging simulated environments. Fadeyev also made notable contributions to the emerging field of tensegrity robotics, where he developed a computer vision system using fiducial markers to estimate the pose of these lightweight, deformable robots in real time. His 2019 paper on this topic (9 citations) tackles the fundamental sensing challenge that has hindered effective control of tensegrity structures. By combining synthetic data generation with marker-based tracking, Fadeyev’s research provides scalable solutions for perception in both conventional and novel robotic platforms, advancing the frontier of autonomous manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2