Samuel Kakuba
Papers
1
Total Citations
2
H-Index
1
About
Samuel Kakuba is a researcher at the forefront of computer vision and autonomous driving perception, with a focused expertise in monocular 3D object detection. His major contribution lies in addressing the inherent depth ambiguity of single-camera systems, a critical challenge for safe navigation. In his notable work, "MonoDGAE: depth-guided attention and bilateral filtering for robust monocular 3D object detection" (2025), Kakuba introduces a novel architecture that leverages depth-guided attention mechanisms and bilateral filtering to significantly improve detection accuracy and robustness. This approach enhances the model's ability to precisely localize objects in three-dimensional space from a single image, directly impacting the reliability of real-world autonomous systems. While his work is early in its citation lifecycle, the technical innovation in MonoDGAE has already garnered attention, marking him as an emerging voice in the field. Kakuba’s research bridges the gap between theoretical depth estimation and practical, noise-resilient detection, offering a promising direction for cost-effective 3D perception in self-driving cars and robotics.
Research Focus
Key Achievements
Top Papers
- 1