Mahindra Sanmugam
Papers
1
Total Citations
8
H-Index
1
About
Mahindra Sanmugam is a rising researcher at the intersection of computer vision, deep learning, and autonomous systems, with a particular focus on bridging the synthetic-to-real domain gap in autonomous driving. His most-cited work, "Synthetic to Real Gap Estimation of Autonomous Driving Datasets using Feature Embedding" (2022, 8 citations), tackles a critical bottleneck in robotics and computer vision: the need for vast, labeled datasets to train generalized deep learning models for tasks like visual odometry, segmentation, and object detection. Rather than relying solely on costly real-world data collection, Sanmugam proposes a novel method to quantify and mitigate the distribution shift between synthetic and real environments, enabling more robust model transfer. This contribution is especially valuable for researchers seeking to leverage simulation for scalable training without sacrificing real-world performance. Though early in his career, Sanmugam’s work addresses a foundational challenge in autonomous driving, and his citation trajectory signals growing recognition. His research offers practical pathways for safer, more data-efficient autonomous systems, making him a promising voice in the field.
Research Focus
Key Achievements
Top Papers
- 1