Uchitha Rajapaksha

Papers

Total Citations

H-Index

About

Uchitha Rajapaksha is a researcher whose work sits at the intersection of computer vision, deep learning, and scene understanding, with a particular focus on depth perception from visual data. His most notable contribution is a landmark 2024 comprehensive survey on deep learning-based depth estimation from monocular images and videos, a technically challenging problem that involves inferring three-dimensional spatial information from a single RGB camera — eliminating the need for expensive specialized hardware. The survey, which has already accumulated 55 citations in a short period, systematically analyzes over 500 deep learning-based approaches published across the past decade, making it an invaluable reference for researchers navigating this rapidly evolving field. The work highlights the broad real-world relevance of monocular depth estimation, spanning critical application domains such as autonomous driving, robotics, 3D reconstruction, and digital entertainment. The strong early citation trajectory of this paper signals its significance as a foundational resource in the community. Rajapaksha's ability to synthesize a vast and complex literature into a coherent, accessible survey reflects both deep domain expertise and a commitment to advancing collective knowledge in computer vision research.