Inderjot Singh Saggu
Papers
1
Total Citations
20
H-Index
1
About
Inderjot Singh Saggu is a researcher in computer vision and deep learning, with a primary focus on self-supervised depth estimation from monocular videos. His most notable contribution is the development of **S³Net (Semantic-Aware Self-supervised Depth Estimation)**, a pioneering framework that integrates semantic understanding into self-supervised depth learning. By leveraging both monocular videos and synthetic data, S³Net significantly improves depth prediction accuracy in challenging scenarios, such as textureless regions and dynamic objects, without requiring ground-truth depth labels. This work, published in 2020, has garnered 20 citations and is recognized for bridging the gap between synthetic and real-world data in self-supervised learning. Saggu’s research addresses a critical limitation in autonomous systems—reliable depth perception in unstructured environments—making his contributions highly relevant for robotics, augmented reality, and autonomous driving. His approach demonstrates how semantic priors can enhance geometric reasoning, offering a scalable solution for training robust depth models. As a researcher, Saggu continues to push the boundaries of self-supervised learning, with his work inspiring further exploration into multimodal and cross-domain depth estimation techniques.
Research Focus
Key Achievements
Top Papers
- 1