Salman Siddique Khan

I am a Postdoctoral Associate at the Department of ECE, Rice University. I am being advised by Dr. Ashu Sabharwal and Dr. Ashok Veeraraghavan. I work in the area of machine learning, computer vision and computational imaging. I finished my Ph.D. from the Computational Imaging Lab, IITM, where I worked under Dr. Kaushik Mitra on computational photography and computer vision. As a Ph.D. candidate, I was awarded the Qualcomm Innovation Fellowship for the year 2020-2021 to work on mask-based lensless cameras. Prior to joining the Ph.D. program at IIT Madras, I completed my undergraduate studies in Electronics and Instrumentation Engineering from the National Institute of Technology Rourkela, India.

Email  /  Google Scholar  /  Github  /  LinkedIn

I'm primarily interested in developing machine learning, computer vision and computational imaging tools. Most of my recent works has been focused on using deep learning to develop novel imaging and image processing pipelines for systems with form-factor, cost and privacy advantages that can have applications in robotics, healthcare and smart wearables.

We propose a double-mask lensless camera that performs encryption in the optical domain.

We propose a novel coded-aperture based dual pixel camera with superior depth and RGB imaging capability.

We propose a learning-based framework for designing phase-masks for ultra-thin lensless cameras.

We propose a novel physics-inspired neural network for fast and accurate RGB-D estimation from single-shot lensless capture.

We propose an unrolled physics-based network for Fourier Ptychographic reconstructions that outperforms existing methods for low dynamic range sensors.

We propose a general learning based framework to recover photorealistic scenes from lensless captures for both separable and non-separable forward models.

We propose a learning based framework for designing the optical and analog components of a privacy enhancing camera.

We propose a learning based solution to recover photorealistic scenes from globally multiplexed lensless measurements.

Website credits to Jon Barron