Papers
1
Total Citations
4
H-Index
1
About
Sumit Mishra is a researcher in computer vision and deep learning, with a primary focus on 3D scene understanding and geometric computer vision. His most notable contribution is the development of RelMobNet, an end-to-end framework for relative camera pose estimation that introduces a robust two-stage training strategy. This work addresses a fundamental challenge in visual odometry and structure-from-motion—accurately estimating the relative orientation and translation between two camera views from monocular images. By leveraging a novel training pipeline that combines synthetic and real-world data, Mishra’s approach achieves state-of-the-art performance on standard benchmarks, demonstrating resilience to challenging conditions like large viewpoint changes and textureless scenes. Though his most-cited paper currently has 4 citations, it represents an emerging contribution that is gaining traction in the robotics and autonomous navigation communities. Mishra’s research bridges the gap between classical geometric methods and modern learning-based techniques, offering practical solutions for applications in augmented reality, drone navigation, and autonomous driving. His work exemplifies how careful architectural design and training strategies can push the boundaries of what is possible in relative pose estimation, making him a promising voice in the field.
Research Focus
Key Achievements
Top Papers
- 1