PhD Student @ MIT
🇮🇳 • 🇾🇪 • 🇪🇸 • 🇺🇸
I am actively looking for UROPs and collaborators to work with on the three research directions. If you’re interested, please fill out this form here. For others, feel free to reach out if you want to talk in any of the areas below!
Kush is a PhD student in the Camera Culture group at the MIT Media Lab advised by Ramesh Raskar. He received his S.M at MIT Media lab in 2023 and BS from the University of Illinois Urbana-Champaign. His research focuses on the intersection of AI, vision, and imaging, aiming to develop innovative imaging systems and algorithms.
Kush’s research lies in the intersection of AI, Computer Vision, and Imaging to automate and accelerate scientific discovery and invention i.e. invent new systems.
1) Generative Design to study the Evolution of Natural Visual Intelligence: Study Natural Visual Intelligence by computationally mimicking biological principles.
2) Generative Design of Artificial Visual Intelligence: Computational design of AI-based vision systems for scientific and engineering applications.
3) Physics-based Machine Learning for Computer Vision and Imaging: Develop novel vision and imaging algorithms by integrating physical principles into machine learning frameworks.
News:
Generative Design of Visual Intelligence
Kushagra Tiwary, Tzofi Klinghoffer*, Aaron Young*, Siddharth Somasundaram, Nikhil Behari, Akshat Dave, Brian Cheung, Dan-Eric Nilsson, Tomaso Poggio, Ramesh Raskar (* Equal Contribution)
MIT Press (coming soon!), 2024
Accelerating Discovery: Using AI to accelerate Science, R&G, and Augment Engineering & Design
Co-Organizer and Speaker at Workshop in Media Lab Member’s week 2023
Talk on: Accelerating R&D and AI-based Vision Stack Design
This workshop explores how AI can accelerate science, R&D processes, and augment engineering with a special emphasis on Research and Development (R&D). We will introduce the "Scientist AI" that can vastly accelerate time-consuming scientific and R&D design processes through case studies from the fields of Autonomous Vehicles, Computational Imaging, Drug Discovery, and Theraputics.
DISeR: Designing Imaging Systems with Reinforcement Learning
Tzofi Klinghoffer*, Kushagra Tiwary*, Nikhil Behari, Bhavya Agarwalla, Ramesh Raskar, ICCV 2023
We propose a new way to co-design imaging systems and task-specific perception models. The camera designer selects imaging hardware candidates, which are used to capture observations in simulation. The perception model is then updated and computes the reward for the camera designer using the captured observations. In our work, we implement the camera designer with reinforcement learning and the perception model with a neural network.
[Project Page] [arXiv] [Video]
Physics-based ML for Computer Vision
Zaid Tasneem, Akshat Dave, Abhishek Singh, Kushagra Tiwary, Praneeth Vepakomma, Ashok Veeraraghavan, Ramesh Raskar
We transform personal images into decentralized Neural Radiance Fields (NeRFs) to create immersive 3D experiences. Our key insight is to decompose users' 3D views into personal and global NeRFs, aggregating only the latter to construct photorealistic scene representations with minimal server computation.
[Project Page] • [Paper] • [Video] • [Talk]
Nikhil Behari, Akshat Dave, Kushagra Tiwary, William Yang, Ramesh Raskar
EARTHVISION CVPR Workshop, 2024
3D modeling from satellite imagery is essential in areas of environmental science, urban planning, agriculture, and disaster response. In this work, we introduce SUNDIAL, a comprehensive approach to 3D reconstruction of satellite imagery using neural radiance fields.
[arXiv]
Objects As Radiance Field Cameras
Kushagra Tiwary*, Akshat Dave*, Nikhil Behari, Tzofi Klinghoffer, Ashok Veeraghavan, Ramesh Raskar, CVPR 2023
We convert objects with unknown geometry into radiance-field cameras to image the world from the object's perspective. Our key insight is to convert the object surface into a virtual sensor that captures cast reflections as a 2D projection of the 5D environment radiance field visible to the object.
[Project Page] • [Paper] • [Code] • [Talk] • [MIT News]
Towards Neural Representations through Shadows
Kushagra Tiwary*, Tzofi Klinghoffer*, Ramesh Raskar,
ECCV 2022
Neural Representations cannot use shadows to learn about hidden information in the scene. We present a method that learns neural shadow fields which are neural scene representations that are only learnt from the shadows present in the scene.
Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imaging
Kushagra Tiwary*, Tzofi Klinghoffer*, Siddharth Somasundaram*, Ramesh Raskar,
ICCP 2022
Cameras were originally designed using physics-based heuristics to capture aesthetic images, but now with the advent of physics-based machine learning, we can design cameras to be task-specific i.e. directly for their intended application!