Meghal Dani
Papers
1
Total Citations
15
H-Index
1
About
Meghal Dani is a computer vision researcher whose work focuses on efficient 3D pose estimation for real-world applications like augmented reality, autonomous navigation, and robotics. Her most cited paper, "3DPoseLite: A Compact 3D Pose Estimation Using Node Embeddings" (2021, 15 citations), introduces a novel methodology that leverages node embeddings to achieve compact and accurate pose estimation, making it ideal for on-device inference where computational resources are limited. This contribution addresses a critical need in the field—balancing model efficiency with accuracy—enabling practical deployment in AR and robotics systems. Dani's work has been recognized for its potential to advance lightweight computer vision solutions, with her research cited by peers exploring similar challenges in pose estimation and embedded systems. Her approach to using node embeddings for spatial reasoning demonstrates a creative intersection of graph theory and computer vision, marking her as an emerging voice in efficient deep learning for real-time applications.
Research Focus
Key Achievements
Top Papers
- 13DPoseLite: A Compact 3D Pose Estimation Using Node Embeddings15 citations · 2021