Center for AI in Computer Vision

At the Center for AI in Computer Vision, we are committed to narrowing the gap between theoretical research in machine learning and its practical applications in real-world scenarios. Our focus is on leveraging cutting-edge AI technologies to tackle complex problems across various domains. Our research and development efforts aim to create intelligent systems that not only advance the field but also make a meaningful impact on society.

Our multidisciplinary research spans several key areas:

Computer Vision: Advancing techniques in visual recognition and scene understanding to enable machines to interpret and interact with the visual world.

Machine Learning & Deep Learning: Designing and training intelligent systems that learn from data to perform tasks with accuracy, efficiency, and adaptability.

Responsible & Explainable AI: Ensuring our technologies are transparent, fair, and accountable. We develop AI systems that stakeholders can understand, trust, and govern.

Research areas

• Sonar and underwater image analysis
• Physics-informed simulation and digital twins
• Synthetic data, sim-to-real transfer and domain adaptation
• Generative models for image synthesis and augmentation

Datasets

The datasets are free for non-commercial research. Access is granted after you submit a request and return a signed Data Use Agreement.

Publications

• Kamal Basha S and Nambiar A., S3simulator: A benchmarking side scan sonar simulator dataset for underwater image analysis, International Conference on Pattern Recognition, 2024.
• Kamal Basha S, Anukul Kiran B, Nambiar A. and Rajendran S., A Novel Context-Adaptive Fusion of Shadow and Highlight Regions for Efficient Sonar Image Classification, OCEANS 2025 - Great Lakes. doi:10.23919/OCEANS59106.2025.11244959

Contact

athiram@srmist.edu.in