Uma Mudenagudi

Papers

Total Citations

H-Index

About

Uma Mudenagudi is a leading researcher in computer vision and robotics, specializing in 3D scene understanding, depth estimation, and human-robot interaction. Her work bridges the gap between sparse sensor data and dense environmental perception, with a focus on enabling intelligent systems to operate in real-world, memory-constrained settings. Her most cited paper, "DeepDNet: Deep Dense Network for Depth Completion Task" (2021, 12 citations), introduces a novel architecture that generates accurate dense depth maps from sparse inputs, a critical contribution for applications like 3D reconstruction and mixed reality. In "LGAfford-Net: A Local Geometry Aware Affordance Detection Network for 3D Point Clouds" (2024, 5 citations), she pioneers affordance detection—identifying regions on objects where interaction is possible—enhancing robotic autonomy and human-robot collaboration. Her earlier work, "Android based wireless gesture controlled robot" (2014, 5 citations), demonstrates practical innovation in intuitive control systems for hazardous environments. Additionally, her research on camera relocalization for memory-restricted devices (2020, 5 citations) addresses key challenges in mobile and embedded systems. With a career marked by impactful contributions to depth completion, affordance detection, and gesture-based robotics, Mudenagudi continues to shape the future of intelligent, perceptive machines.