Muhammad Rameez Ur Rahman
Sapienza University of Rome, Ca' Foscari University of Venice
Papers
2
Total Citations
15
H-Index
2
About
Muhammad Rameez Ur Rahman is a rising researcher in computer vision and assistive robotics, with a focus on RGB-D salient object detection and open-vocabulary 3D perception. His most-cited work, "Boosting RGB-D salient object detection with adaptively cooperative dynamic fusion network" (2022, 13 citations), introduces a novel deep learning architecture that dynamically fuses color and depth features to improve detection accuracy in complex scenes—a critical advancement for autonomous navigation and human-robot interaction. More recently, his paper "OpenNav: Efficient Open Vocabulary 3D Object Detection for Smart Wheelchair Navigation" (2025) pioneers the integration of open-vocabulary detection into assistive mobility systems, enabling wheelchairs to recognize and avoid arbitrary objects without pre-defined categories. This work bridges state-of-the-art AI with real-world accessibility, demonstrating strong potential for impact in inclusive technology. With his innovative fusion techniques and commitment to practical applications, Rahman is establishing himself as a key contributor at the intersection of deep learning, 3D scene understanding, and assistive robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2