• Login
  • Register

Work for a Member company and need a Member Portal account? Register here with your company email address.

Making the invisible visible–inside our bodies, around us, and beyond–for health, work, and connection

Copyright

Camera Culture

Camera Culture

Group Contact:
Project Research

MIT NANDA: Algorithms to Unlock The Internet of AI Agents

NANDA (Networked Agents and Decentralized AI) is an ambitious MIT initiative developing the foundational infrastructure for a true "Interne…
Project Research

Large Population Models

Think about how a delayed shipment, a cancelled flight, or a glitchy app can disrupt your week. Now scale that up: a virus like COVID-19 co…
Project Research

MIT Kumbhathon: A City-Stack Powered by Decentralized AI

​A City-Stack Powered by Decentralized AIOverviewMIT Kumbhathon, hosted at the MIT Media Lab, is pioneering a revolutionary approach t…
Project Research

Data Acquisition via Experimental Design for Data Markets

The acquisition of training data is crucial for machine learning applications. Data markets can increase the supply of data, particularly i…
Project Research

Decentralized AI

As AI evolves beyond screen assistants and into dimensional applications, decentralization emerges as the critical factor for unlocking i…
Project Research

First 100 days of pandemic; an interplay of pharmaceutical, behavioral and digital interventions - A study using agent based modeling

The challenge of understanding pandemics, illustrated by the recent COVID-19 outbreak, has significantly impacted global health and economi…
Project Research

Objects as Cameras

Press: - MIT News:  Using reflections to see the world from new points of view- TechXplore, EuropaPress, La Nacion …
Project Research

Posthoc Privacy guarantees for neural network queries

Cloud based machine learning inference is an emerging paradigm where users query with their data to a service provider who runs a ML model …
Project Research

Task-Agnostic Data Valuation

Data is the main fuel of the modern world, enabling artificial intelligence and driving technological growth. The demand for data has grown…
Project Research

Computational Privacy for Computer Vision

Computer Vision applications are making a remarkable impact on society and advancing progress in Machine Learning. Our project aims to desi…
Project Research

Detecting and Mapping Transparent or Mirror-like Surfaces with Lidar

Although lidar is widely used for mapping the 3D geometry of surfaces, the technology has historically been challenged by specular, or mirr…
Project Research

Private Machine Learning on Point Clouds

Point clouds are an increasingly ubiquitous input modality and the raw signal can be efficiently processed with recent progress in deep lea…
Project Research

Image-based Virtual Try-On

Image-based virtual try-on involves synthesizing perceptually convincing images of a model wearing a particular garment and has garnered si…
Project Research

What can we learn from predicting shadows?

By predicting sparse shadow cues, our physics-inspired machine learning algorithm can reconstruct the underlying 3D scene. Abstract. W…
Project Research

Benchmarking Privacy in Machine Learning Prediction

We tackle the question of how to benchmark reconstruction of inputs from deep neural networks representations. This inverse problem is of g…
Project Research

PrivateMail: Supervised Manifold Learning of Deep Activations With Privacy

Differential Privacy offers strong guarantees such as immutable privacy under any post-processing. In this work, we propose a differentiall…
Project Research

QCSF: Parallel Combinatorial Optimization without needing Submodularity

Classes of set functions along with a choice of ground set are a bedrock to determine and develop corresponding variants of greedy algorith…
Project Research

Private measurement of nonlinear correlations between multiple parties

We introduce a differentially private method to measure nonlinear correlations between sensitive data hosted across two entities. We provid…
Project Research

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

Wireless channels can be inherently privacy-preserving by distorting the received signals due to channel noise, and superpositioning multip…
Project Research

Synthesizing data privately for Machine Learning

We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in var…
Project Research

DeepABM: Data-driven public policy with differentiable simulators

Abstract:We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for s…
Project Research

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks

Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer…
Project Research

FedML: A Research Library and Benchmark for Federated Machine Learning

In this work, we introduce FedML, an open research library and benchmark that facilitates the development of new 'federated learning algori…
Project Research

NoPeek

NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training (Won FG-2021 Mukh Best Paper Runner…
Project Research

DAMS: Differentially Private Sketching Data Structures

We propose an improved private count-mean-sketch data structure and show its applicability to differentially private contact trac…
Project Research

Splintering with distributions: A stochastic decoy scheme for private computation

We present a stochastic scheme for splitting the client data into privatized shares that are transmitted to the server in such settings. Th…
Project Research

Safe Paths

Papers from SafePaths: https://github.com/PrivateKit/PrivacyDocumentsSafe Paths is an MIT-led, free, open source technology that …
Project Research

Split Learning: Distributed and collaborative learning

Split Learning: Distributed deep learning without sharing raw data Project Page: https://splitlearning.github.io/Abstract: C…
Project Research

Time-folded optics

Rethinking photography optics in the time dimensionWhat if we could design optics in time instead of space?
Project Research

Seeing Through Realistic Fog

Seeing through dense, dynamic, and heterogeneous fog conditions. The technique, based on visible light, uses hardware that is similar to LI…
Project Research

High-frequency LIDAR using beat notes

Time of Flight 3D cameras like the Microsoft Kinect are prevalent in computer vision and computer graphics. In such devices, the power of a…
Project Research

Calibration Invariant Imaging

Object Classification through Scattering Media with Deep LearningA method for classifying objects hidden behind a scattering layer wit…
Project Research

Architecture selection for deep neural networks

We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures…
Project Research

Efficient lensless imaging with a femto-pixel

Lensless imaging with compressive ultrafast sensingTraditional cameras require a lens and a mega-pixel sensor to capture images. The lens f…
Project Research

Food sensing on smartphones

We demonstrate a smartphone based spectrometer design that is standalone and supported on a wireless platform. The device is inherently low…
Project Research

Reading Through a Closed Book

Terahertz time-gated spectral imaging for content extraction through layered structures.
Project Research

Imaging with All Photons

How to see through tissueWe demonstrate a new method to image through scattering materials like tissue and fog. The demonstration includes …
Project Research

The Next 30 Years of VR

In this visual brainstorming, we present the next 30 years of VR in a set of concept designs.
Project Research

Skin Perfusion Photography

Skin and tissue perfusion measurements are important parameters for diagnosis of wounds and burns, and for monitoring plastic and reconstru…
Project Research

Optical Brush: Enabling deformable imaging interfaces

Our deformable camera exploits new, flexible form factors for imaging in turbid media. In this study we enable a brush-like form factor wit…
Project Research

Health-tech innovations with Tata Trusts, Mumbai

We believe that tough global health problems require an innovation pipeline. We must bring together the people and providers facing health …
Project Research

Blind and reference-free fluorescence lifetime estimation via consumer time-of-flight sensors

Fluorescence lifetime imaging is a significant bio-imaging tool that finds important applications in life-sciences. Widely known applicatio…
Project Research

AnEye: Extending the reach of anterior segment ophthalmic imaging

Eye exams via a slit lamp are critical in early diagnosis of diseases such as cataracts, corneal injury, and pterygia, in order to avert vi…
Project Research

Beyond the Self-Driving Car

This concept gallery shows the chain of startups and ideas that will follow after the emergence of self-driving cars.
Project Research

Nashik Smart Citizen Collaboration with TCS

We believe that tough global health problems require an innovation pipeline. We must bring together the people and providers facing health …
Project Research

Hyderabad eye health collaboration with LVP

We believe that tough global health problems require an innovation pipeline. We must bring together the people and providers facing health …
Project Research

Towards In-Vivo Biopsy

A new method to detect and distinguish between different types of fluorescent materials. The suggested technique has provided a dramaticall…
Project Research

Looking Around Corners

Using a femtosecond laser and a camera with a time resolution of about one trillion frames per second, we recover objects hidden out of sig…
Project Research

Time-of-Flight Microwave Camera

Our architecture takes a hybrid approach to microwaves and treats them like waves of light. Most other work places antennas in a 2D arrange…
Project Research

Single-Photon Sensitive Ultrafast Imaging

The ability to record images with extreme temporal resolution enables a diverse range of applications, such as time-of-flight depth imaging…
Project Research

Identi-Wheez: A device for in-home diagnosis of asthma

Asthma is the most common chronic illness among children. The skills required to diagnose it make it an even greater concern. Our solution …
Project Research

Unbounded high dynamic range photography using a modulo camera

We present a novel framework to extend the dynamic range of images called Unbounded High Dynamic Range (UHDR) photography with a modulo cam…
Project Research

Imaging Behind Diffusive Layers

Locating and classifying florescent tags behind turbid layers using time-resovled inversion Using time resolved and sparse optimizatio…
Project Research

Inverse problems in time-of-flight imaging

We are exploring mathematical modeling of time-of-flight imaging problems and solutions.
Project Research

New methods in time-of-flight imaging

Time-of-flight (ToF) cameras are commercialized consumer cameras that provide a depth map of a scene, with many applications in computer vi…
Project Research

Portable Retinal Imaging

The major challenge in preventing blindness is identifying patients and bringing them to specialty care. Diseases that affect the retina, t…
Project Research

Trillion Frames Per Second Camera

We have developed a camera system that captures movies at an effective rate of approximately one trillion frames per second. In one frame o…
Project Research

NETRA: Smartphone add-on for eye tests

Can a person look at a portable display, click on a few buttons, and recover his or her refractive condition? Our optometry solution combin…
Project Research

Imaging through scattering media using femtophotography

We use time-resolved information in an iterative optimization algorithm to recover reflectance of a three-dimensional scene hidden behind a…
Project Research

Reflectance acquisition using ultrafast imaging

We demonstrate a new technique that allows a camera to rapidly acquire reflectance properties of objects "in the wild" from a single viewpo…