Girish Hegde
Papers
1
Total Citations
12
H-Index
1
About
Girish Hegde is a researcher at the forefront of computer vision and deep learning, with a focused expertise in 3D scene understanding and depth estimation. His most notable contribution is the development of DeepDNet (Deep Dense Network for Depth Completion Task), a pioneering architecture that transforms sparse depth data into dense, accurate depth maps. This work, published in 2021, addresses a critical bottleneck in applications ranging from 3D reconstruction and mixed reality to autonomous robotics, where precise depth perception is essential. With 12 citations, DeepDNet has already demonstrated its value in bridging the gap between sparse sensor inputs and the dense depth information required for real-world systems. Hegde’s research is characterized by its practical impact, offering efficient solutions that enhance the reliability of scene understanding technologies. His achievements reflect a commitment to advancing deep learning methods that directly enable next-generation spatial intelligence, making him a promising voice in the evolving landscape of computer vision and its applied domains.
Research Focus
Key Achievements
Top Papers
- 1DeepDNet: Deep Dense Network for Depth Completion Task12 citations · 2021