Praveen Kumar Rajendran
Papers
1
Total Citations
4
H-Index
1
About
Praveen Kumar Rajendran is a computer vision researcher whose work centers on geometric deep learning and 3D scene understanding, with a particular focus on robust camera pose estimation. His most notable contribution is the development of RelMobNet, an end-to-end framework for relative camera pose estimation that employs a robust two-stage training strategy. This work, published in 2023, addresses the critical challenge of accurately determining the spatial relationship between two camera views—a fundamental problem for applications in autonomous navigation, augmented reality, and robotics. By introducing a training methodology that first learns robust feature correspondences before refining pose regression, Rajendran’s approach achieves state-of-the-art performance on challenging benchmarks, demonstrating resilience to large viewpoint changes and textureless scenes. While his citation count is still growing, the technical novelty of RelMobNet has already garnered attention within the community, and his work represents an important step toward more reliable visual localization systems. Rajendran’s research sits at the intersection of deep learning and geometric reasoning, pushing the boundaries of how machines perceive and navigate the 3D world.
Research Focus
Key Achievements
Top Papers
- 1