Kushagra Tiwary

PhD Student @ MIT

🇮🇳 • 🇾🇪 • 🇪🇸 • 🇺🇸

In Typography Outline

email: ktiwary [at] mit [dot] edu

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:



Button

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.

Button

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.

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!

In Typography Outline

email: ktiwary [at] mit [dot] edu

I am always open to chat about interesting ideas in this field! Reach out if you want to ​talk in any of the areas!