Research Portfolio & Publications

Developing smart systems to handle extreme lighting variability in real-world environments.

Highly efficient neural networks designed for mobile devices and edge computing.

End-to-End deep learning network using Triplet Content Loss for weather synthesis.

Joint training of dehazing and super-resolution models to reduce computation.

Face Shape Classification and Swapping for personalized recommendation.

Improving the resolution of drone-based aerial images for better object detection.

Real-time public safety monitoring with YOLO-based detection and tracking.