Diana Wofk

Papers

Total Citations

H-Index

About

Diana Wofk is a researcher whose work sits at the intersection of computer vision and efficient deep learning, with a primary focus on enabling advanced perception for resource-constrained systems. Her most notable contribution is the development of **FastDepth**, a pioneering framework for fast monocular depth estimation on embedded platforms. This work, which has garnered 22 citations, directly addressed a critical bottleneck in robotics: the need for accurate, real-time depth sensing from a single RGB camera on low-power devices. By designing a novel, efficient network architecture, Wofk demonstrated that state-of-the-art depth estimation could be achieved without the computational overhead of traditional stereo or LiDAR systems. This breakthrough has significant implications for autonomous navigation, obstacle detection, and localization in drones, mobile robots, and augmented reality. Her research elegantly balances algorithmic accuracy with practical deployability, making her a key figure in the push toward truly autonomous, on-device intelligence.