Carlos Pereira
Papers
1
Total Citations
3
H-Index
1
About
Carlos Pereira is a researcher whose work lies at the intersection of computer vision, robotics, and high-performance computing. His primary research areas include real-time 3D reconstruction, Simultaneous Localization and Mapping (SLAM), and algorithm parallelization. Pereira’s major contribution is the pragma-oriented parallelization of the Direct Sparse Odometry (DSO) SLAM algorithm, a breakthrough that addresses the critical challenge of achieving real-time monocular 3D reconstruction. By leveraging directive-based parallel programming, he significantly improved the computational efficiency of SLAM systems without sacrificing accuracy, enabling faster and more practical deployment in resource-constrained environments like autonomous vehicles and mobile robotics. His 2019 paper on this topic has garnered 3 citations, reflecting its niche but foundational impact in the SLAM community. Pereira’s work is notable for bridging the gap between theoretical computer vision and real-world engineering constraints, offering a pragmatic solution to a notoriously difficult problem. His research continues to inspire efforts toward more efficient, real-time spatial mapping systems, making him a valuable contributor to the field of autonomous perception.
Research Focus
Key Achievements
Top Papers
- 1