Raunak Shah
Papers
1
Total Citations
20
H-Index
1
About
Raunak Shah is a researcher advancing the field of computer vision, with a primary focus on self-supervised depth estimation and semantic scene understanding. His most notable contribution, the S³Net framework, introduces a novel approach that leverages monocular videos and synthetic data to achieve semantic-aware self-supervised depth estimation, bridging the gap between real-world and simulated environments. This work, which has garnered 20 citations, demonstrates his ability to integrate geometric and semantic cues without relying on costly ground-truth depth labels, making depth perception more scalable and robust. Shah’s research addresses critical challenges in autonomous navigation and 3D reconstruction, where accurate depth from single images is essential. By combining synthetic data with real-world video streams, his methods enhance generalization across diverse scenes, a key achievement in reducing domain shift. His work stands out for its practical impact, offering a pathway to more efficient training pipelines for depth estimation models. As a rising voice in self-supervised learning, Shah’s contributions are paving the way for more intelligent and adaptable visual systems, promising to influence both academic research and real-world applications in robotics and augmented reality.
Research Focus
Key Achievements
Top Papers
- 1