Karthik Narayan

Papers

Total Citations

401

H-Index

About

Karthik Narayan is a leading researcher in computer vision and robotics, with a focus on 3D object perception and high-fidelity reconstruction. His most influential work, the BigBIRD dataset (322 citations), established a gold-standard benchmark for large-scale 3D object instance recognition, providing pose-annotated, multi-view RGB-D data that has driven advances in robotic grasping and visual recognition. Narayan pioneered multimodal blending techniques for high-accuracy instance recognition (56 citations), demonstrating how fusing depth and color information from commodity sensors like the Microsoft Kinect can achieve robust detection in cluttered tabletop environments. He further advanced 3D scanning by developing novel methods that fuse range sensor data with silhouette information (17 citations) and optimized color models (6 citations) to produce high-quality, photorealistic 3D meshes from affordable RGB-D cameras. His contributions directly enable practical applications in robot vision, virtual reality, and online shopping, bridging the gap between raw sensor data and usable 3D models. Narayan’s work continues to shape how autonomous systems perceive and interact with the physical world.