Vishakh Hegde

Papers

Total Citations

168

H-Index

About

Vishakh Hegde is a researcher specializing in 3D computer vision, deep learning, and multimodal data representation. His most notable contribution is **FusionNet** (2016), a pioneering architecture for 3D object classification that combines multiple data representations — volumetric and multi-view — to achieve state-of-the-art results on the Princeton ModelNet benchmark, one of the field's most competitive challenges. By demonstrating that fusing complementary data modalities significantly improves recognition accuracy, Hegde's work helped establish a foundational paradigm in 3D object understanding that influenced subsequent research in autonomous robotics, scene understanding, and point cloud processing. FusionNet has accumulated 168 citations, reflecting its meaningful impact on the computer vision and robotics communities, where robust 3D object recognition is a critical capability. His research sits at the intersection of geometric deep learning and practical vision systems, addressing a core challenge in enabling machines to perceive and interpret three-dimensional environments. Hegde's work remains a relevant reference point for researchers exploring how neural networks can leverage heterogeneous input representations to overcome the limitations of any single data modality in complex recognition tasks.