Karthik Pujar
Papers
1
Total Citations
10
H-Index
1
About
Karthik Pujar is a computer vision researcher whose work focuses on advancing indoor scene understanding through deep learning. His most cited paper, "Combining RGB and Depth Images for Indoor Scene Classification Using Deep Learning" (2017, 10 citations), addresses a critical challenge in robotics and autonomous systems: the high appearance variability of indoor environments. Pujar’s key contribution lies in demonstrating how fusing RGB and depth modalities significantly improves classification accuracy over traditional single-modality approaches, a technique that has become foundational for indoor mobile robotics and scene recognition. While his citation count reflects the niche and emerging nature of this field, his work has been instrumental in pushing forward the practical deployment of vision systems in cluttered, dynamic indoor spaces. Pujar’s research sits at the intersection of deep learning, sensor fusion, and spatial AI, offering a pathway for more robust perception in applications ranging from service robots to augmented reality. His findings continue to influence subsequent studies on multimodal scene classification, marking him as a thoughtful contributor to the evolving landscape of indoor visual intelligence.
Research Focus
Key Achievements
Top Papers
- 1