Mohammed Bennamoun
Papers
18
Total Citations
2,644
H-Index
10
About
Mohammed Bennamoun is a leading figure in computer vision and robotics, renowned for his pioneering work in 3D perception, deep learning, and object recognition. His research has fundamentally advanced how machines understand and interact with the three-dimensional world. His landmark survey, "Deep Learning for 3D Point Clouds: A Survey" (2020), has garnered over 2,200 citations, establishing it as an essential resource for researchers in autonomous driving and robotics. Bennamoun has made significant contributions to RGB-D perception, developing novel frameworks like hierarchical cascaded forests for simultaneous object recognition and grasp detection, and pioneering real-time pose estimation for rigid objects. His recent comprehensive survey on deep learning-based depth estimation from monocular images (2024) further cements his role as a thought leader in the field. Beyond these, his work spans human interaction prediction, semantic scene completion, and adversarial attack detection, consistently pushing the boundaries of 3D computer vision. With a career marked by high-impact publications and a focus on practical, real-world applications, Bennamoun’s research continues to shape the future of intelligent robotic systems and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1Deep Learning for 3D Point Clouds: A Survey2,225 citations · 2020
- 2RGB-D Object Recognition and Grasp Detection Using Hierarchical Cascaded Forests157 citations · 2017
- 3
- 4Human Interaction Prediction Using Deep Temporal Features49 citations · 2016
- 5Deep Learning for 3D Point Clouds: A Survey48 citations · 2019
- 6Semantic scene completion with dense CRF from a single depth image33 citations · 2018
- 7Real-time pose estimation of rigid objects using RGB-D imagery15 citations · 2013
- 8Evolutionary Feature Learning for 3-D Object Recognition10 citations · 2017
- 9Efficient Detection of Pixel-Level Adversarial Attacks10 citations · 2020
- 10Automated 3D model‐based free‐form object recognition10 citations · 2004