Vaishakh Nargund
Papers
1
Total Citations
12
H-Index
1
About
Vaishakh Nargund is a researcher whose work sits at the intersection of computer vision and deep learning, with a particular focus on 3D scene understanding and depth perception. His most cited contribution, "DeepDNet: Deep Dense Network for Depth Completion Task" (2021, 12 citations), addresses a critical challenge in robotics and mixed reality: generating accurate, dense depth maps from sparse depth inputs. This work is foundational for applications like 3D reconstruction and autonomous navigation, where reliable depth information is essential. Nargund’s research demonstrates a clear commitment to bridging the gap between sparse sensor data and the dense, high-fidelity representations needed for real-world deployment. By proposing novel deep network architectures, he has contributed to making depth completion more efficient and robust. His work is particularly relevant for students and researchers exploring how deep learning can solve practical perception problems in constrained environments. With a growing citation footprint, Nargund is establishing himself as a promising voice in the field, advancing the tools that power next-generation spatial intelligence systems.
Research Focus
Key Achievements
Top Papers
- 1DeepDNet: Deep Dense Network for Depth Completion Task12 citations · 2021