K. Madhava Krishna

Papers

Total Citations

H-Index

About

K. Madhava Krishna is a prominent researcher specializing in computer vision, robotics, and autonomous navigation, with a particular focus on geometric deep learning and visual perception systems. His work bridges theoretical innovation with practical robotic applications, tackling fundamental challenges in how machines perceive and interpret their environments. Krishna's most notable recent contribution, "ReF — Rotation Equivariant Features for Local Feature Matching" (2022), demonstrates his commitment to advancing sparse local feature matching — a cornerstone capability for robotics and computer vision tasks. Rather than relying solely on conventional data augmentation strategies, his approach introduces rotation equivariant features that meaningfully improve robustness to challenging appearance conditions and varying viewpoints. This represents a principled geometric approach to a long-standing problem in the field. His research has garnered recognition within the scientific community, with his works accumulating citations that reflect their relevance to active research challenges in simultaneous localization and mapping (SLAM), visual odometry, and scene understanding. Krishna's contributions are particularly valuable for researchers working at the intersection of deep learning and robotics perception, offering methodologies that enhance the reliability of autonomous systems operating in complex, real-world environments.