Shishir Reddy Vutukur

Papers

Total Citations

H-Index

About

Shishir Reddy Vutukur is a researcher at the forefront of computer vision and robotics, specializing in 6D object pose estimation—a critical technology for robotic grasping and augmented reality. His work addresses the fundamental challenge of enabling machines to perceive and interact with objects in three-dimensional space without relying on expensive, high-fidelity training data. Vutukur’s major contribution, exemplified in his highly cited paper “NeRF-Feat: 6D Object Pose Estimation using Feature Rendering” (2024, 3 citations), introduces a novel approach that leverages feature rendering from Neural Radiance Fields (NeRF). This method dramatically reduces the need for precise CAD models or complex labeled datasets, instead learning pose estimation from weakly labeled data—a practical breakthrough for real-world deployment. His follow-up work, “Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences” (2024, 1 citation), further refines orientation estimation by integrating shape priors with correspondence matching. Vutukur’s research is notable for its focus on bridging the gap between synthetic training and real-world application, making pose estimation more accessible and robust. His innovative use of NeRF for feature learning represents a significant step toward scalable, cost-effective robotic perception systems.