Sumanth Chennupati
Papers
1
Total Citations
5
H-Index
1
About
Sumanth Chennupati’s research focuses on computer vision and deep learning, with a particular emphasis on monocular depth estimation—a critical task for autonomous driving, robotics, and augmented reality. His most cited work, “A Comparative Study of Different CNN Encoders for Monocular Depth Prediction” (2019), systematically evaluates various convolutional neural network architectures for predicting depth from a single RGB image, providing valuable benchmarks and insights for the field. This paper has garnered 5 citations, reflecting its utility as a reference for researchers seeking to optimize encoder backbones for depth perception tasks. Chennupati’s contributions lie in bridging the gap between theoretical model comparisons and practical deployment, helping to advance methods that replace expensive depth sensors with purely visual cues. His work underscores the importance of rigorous empirical analysis in pushing the boundaries of scene understanding, making him a thoughtful contributor to the growing body of research on efficient, sensor-free depth prediction.
Research Focus
Key Achievements
Top Papers
- 1