Mostafa Mansour: Advancing monocular vision in robotics and autonomous systems

In his doctoral dissertation, MSc (Tech) Mostafa Mansour explored and advanced monocular depth estimation techniques in robotic applications. He focused particularly on integrating ego-motion, semantic priors, and deep learning-based methods to improve estimation accuracy and robustness. His findings make it easier to use monocular vision for depth perception in robotics, self-driving systems and virtual reality.

Depth estimation is a fundamental problem in computer vision and robotics, enabling machines to perceive and interact with their surroundings in three dimensions. Accurate depth perception is critical for applications such as autonomous navigation, robotic manipulation, augmented reality, and 3D scene reconstruction. The monocular depth estimation, which extracts depth information from a single camera, offers a cost-effective and flexible alternative to traditional stereo vision methods like LiDAR.

In his research, Mostafa Mansour systematically evaluated the comparative advantages of monocular and stereo depth estimation, analysing their error characteristics and identifying their optimal use cases.

Beyond depth estimation, Mansour investigated the role of monocular depth information in Simultaneous Localization and Mapping (SLAM), and photorealistic scene reconstruction. With the emergence of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS) as state-of-the-art methods for scene representation, his work explores the integration of monocular depth estimation within the 3DGS framework.

“The developed method enables photorealistic 3D scene reconstruction and scene understanding from monocular camera inputs, offering a viable alternative to depth sensor-based mapping techniques,” says Mostafa Mansour.

Mansour's findings contribute to making monocular vision-based depth perception more accessible and practical for real-world applications in robotics, autonomous systems, and immersive virtual environments.

Public defence on Tuesday 19 August

The doctoral dissertation of MSc (Tech) Mostafa Mansour in the field of Engineering Sciences titled On Monocular Depth Estimation for Scene Understanding in Robotics Applications will be publicly examined at the Faculty of Engineering and Natural Sciences at Tampere University at 13:00 on Tuesday 19 Aug 2025 at Hervanta Campus, Konetalo building, in the auditorium K1702 (Korkeakoulunkatu 6, 33720, Tampere).

The Opponent will be Associate Professor Panagiotis Papadakis from IMT Atlantique university, France. The Custos will be Professor Esa Rahtu from Tampere University.

The doctoral dissertation is available online.

The public defence can be followed via remote connection.