Dikshit Hegde

Papers

Total Citations

H-Index

About

Dikshit Hegde is a researcher at the intersection of 3D computer vision, robotics, and human-robot interaction. His work focuses on enabling machines to perceive and interact with three-dimensional environments in ways that mirror human spatial understanding. Hegde’s key contributions lie in affordance detection—identifying regions on objects where interaction is possible—and in camera relocalization for memory-constrained devices. In his highly cited paper “LGAfford-Net: A Local Geometry Aware Affordance Detection Network for 3D Point Clouds” (2024, 5 citations), he introduces a novel architecture that leverages local geometric features to predict interaction regions, advancing how robots understand object functionality. His earlier work, “Relocalization of Camera in a 3D Map on Memory Restricted Devices” (2020, 5 citations), addresses the critical challenge of maintaining accurate camera pose estimation on devices with limited computational resources, a practical problem for mobile robotics and augmented reality. Hegde’s research demonstrates a clear trajectory from foundational localization techniques to cutting-edge affordance reasoning, with each paper earning early recognition. His work is particularly notable for bridging geometric perception with functional understanding, making him a promising voice in the next generation of embodied AI researchers.