Soumya Jahagirdar

Papers

Total Citations

H-Index

About

Soumya Jahagirdar is a researcher advancing the field of computer vision, with a primary focus on depth estimation and completion for 3D scene understanding. Her most cited work, "DeepDNet: Deep Dense Network for Depth Completion Task" (2021), tackles the critical challenge of generating dense depth maps from sparse depth inputs—a problem central to applications in robotics, autonomous navigation, and mixed reality. By proposing a deep dense network architecture, Jahagirdar's contribution enables more accurate and robust depth perception, directly supporting technologies that rely on precise spatial awareness. With 12 citations, this paper has already garnered attention for its practical relevance in bridging the gap between sparse sensor data and dense scene reconstruction. Her research sits at the intersection of deep learning and geometric computer vision, addressing real-world constraints where computational efficiency and accuracy are paramount. Jahagirdar's work is particularly valuable for students and engineers developing systems for 3D reconstruction, augmented reality, or autonomous agents, offering a clear methodology for improving depth map quality in dynamic environments.