Research
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.
|
|
OpEnCam: Lensless Optical Encryption Camera
Salman S. Khan, Xiang Yu, Kaushik Mitra, Manmohan Chandraker, Francesco Pittaluga
IEEE Transactions on Computational Imaging, 2024
We propose a double-mask lensless camera that performs encryption in the optical domain.
|
|
CADS: Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging
Bhargav Ghanekar, Salman S. Khan, Vivek Boominathan, Pranav Sharma, Shreyas Singh, Kaushik Mitra, Ashok Veeraraghavan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
We propose a novel coded-aperture based dual pixel camera with superior depth and RGB imaging capability.
|
|
Designing Optics and Algorithms for Ultra-thin, High-speed Lensless
Cameras
Salman S. Khan, Vivek Boominathan, Ashok Veeraraghavan, Kaushik Mitra
International Conference on Multimedia and Expo (ICME), 2023
We propose a learning-based framework for designing phase-masks for ultra-thin lensless cameras.
|
|
FlatNet3D: Intensity and Absolute Depth from Single-shot Lensless Capture
Dhruvjyoti Bagadthey*, Sanjana Prabhu*, Salman S. Khan*, Tony Fredrick,Vivek Boominathan, Ashok Veeraraghavan, Kaushik Mitra
Journal of the Optical Society of America A, 2022
We propose a novel physics-inspired neural network for fast and accurate RGB-D estimation from single-shot lensless capture.
|
|
LWGNet: Learned Wirtinger Gradients for Fourier Ptychographic Phase Retrieval
Atreyee Saha, Salman S. Khan, Sagar Sehrawat, Sanjana Prabhu, Shanti Bhattacharya, Kaushik Mitra
European Conference on Computer Vision (ECCV), 2022
We propose an unrolled physics-based network for Fourier Ptychographic reconstructions that outperforms existing methods for low dynamic range sensors.
|
|
FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements
Salman S. Khan, Varun Sundar, Vivek Boominathan, Ashok Veeraraghavan, Kaushik Mitra
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
We propose a general learning based framework to recover photorealistic scenes from lensless captures for both separable and non-separable forward models.
|
|
CAnOPIC: Pre-Digital Privacy-Enhancing Encodings for Computer Vision
Jasper Tan, Salman S. Khan, Vivek Boominathan, Jeffrey Byrne, Richard Baraniuk, Kaushik Mitra, Ashok Veeraraghavan
International Conference on Multimedia and Expo (ICME), 2020 (Oral)
We propose a learning based framework for designing the optical and analog components of a privacy enhancing camera.
|
|
Towards Photorealistic Reconstruction of Highly Multiplexed Lensless Images
Salman S. Khan, Adarsh V.R., Vivek Boominathan, Jasper Tan, Ashok Veeraraghavan, Kaushik Mitra
International Conference on Computer Vision (ICCV), 2019 (Oral)
We propose a learning based solution to recover photorealistic scenes from globally multiplexed lensless measurements.
|
|