Press: - MIT News: Using reflections to see the world from new points of view- TechXplore, EuropaPress, La Nacion …
Cloud based machine learning inference is an emerging paradigm where users query with their data to a service provider who runs a ML model …
Data is the main fuel of the modern world enabling artificial intelligence and driving technological growth. The demand for data has grown …
Computer Vision applications are making a remarkable impact on society and advancing progress in Machine Learning. Our project aims to desi…
By predicting sparse shadow cues, our physics-inspired machine learning algorithm can reconstruct the underlying 3D scene. Abstract. W…
Point clouds are an increasingly ubiquitous input modality and the raw signal can be efficiently processed with recent progress in deep lea…
We tackle the question of how to benchmark reconstruction of inputs from deep neural networks representations. This inverse problem is of g…
We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in var…
Differential Privacy offers strong guarantees such as immutable privacy under any post-processing. In this work, we propose a differentiall…
Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer…
In this work, we introduce FedML, an open research library and benchmark that facilitates the development of new 'federated learning algori…
We present a stochastic scheme for splitting the client data into privatized shares that are transmitted to the server in such settings. Th…
Governments and researchers around the world are implementing digital contact tracing solutions to stem the spread of infectious disease, n…
Papers from SafePaths: https://github.com/PrivateKit/PrivacyDocumentsSafe Paths is an MIT-led, free, open source technology that …
Split Learning: Distributed deep learning without sharing raw data Project Page: https://splitlearning.github.io/Abstract: C…
Rethinking photography optics in the time dimensionWhat if we could design optics in time instead of space?
3D interaction is a magical way for users to interact with a system without touching it. This is usually accomplished using a camera, but t…
Audio on a mobile device can be used to form low-resolution 3D images. The resolution of audio ranging and imaging is heavily limited by ba…
Seeing through dense, dynamic, and heterogeneous fog conditions. The technique, based on visible light, uses hardware that is similar to LI…
Time of Flight 3D cameras like the Microsoft Kinect are prevalent in computer vision and computer graphics. In such devices, the power of a…
Object Classification through Scattering Media with Deep LearningA method for classifying objects hidden behind a scattering layer wit…
Lensless imaging with compressive ultrafast sensingTraditional cameras require a lens and a mega-pixel sensor to capture images. The lens f…
We believe that tough global health problems require an innovation pipeline. We must bring together the people and providers facing health …
Asthma is the most common chronic illness among children. The skills required to diagnose it make it an even greater concern. Our solution …
This concept gallery shows the chain of startups and ideas that will follow after the emergence of self-driving cars.
In this visual brainstorming, we present the next 30 years of VR in a set of concept designs.
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…
How to see through tissueWe demonstrate a new method to image through scattering materials like tissue and fog. The demonstration includes …
The ability to record images with extreme temporal resolution enables a diverse range of applications, such as time-of-flight depth imaging…
Fluorescence lifetime imaging is a significant bio-imaging tool that finds important applications in life-sciences. Widely known applicatio…
Locating and classifying florescent tags behind turbid layers using time-resovled inversion Using time resolved and sparse optimizatio…
A smartphone based spectrometer design that is standalone and supported on a wireless platform. The device is low-cost and the power consum…
A new method to detect and distinguish between different types of fluorescent materials. The suggested technique has provided a dramaticall…
Our architecture takes a hybrid approach to microwaves and treats them like waves of light. Most other work places antennas in a 2D arrange…
Skin and tissue perfusion measurements are important parameters for diagnosis of wounds and burns, and for monitoring plastic and reconstru…
We present a novel framework to extend the dynamic range of images called Unbounded High Dynamic Range (UHDR) photography with a modulo cam…
Traditional medical ultrasound assumes that we are imaging ideal liquids. We are interested in imaging muscle and bone as well as measuring…
We are exploring mathematical modeling of time-of-flight imaging problems and solutions.
Our deformable camera exploits new, flexible form factors for imaging in turbid media. In this study we enable a brush-like form factor wit…
Time-of-flight (ToF) cameras are commercialized consumer cameras that provide a depth map of a scene, with many applications in computer vi…
We use time-resolved information in an iterative optimization algorithm to recover reflectance of a three-dimensional scene hidden behind a…
The major challenge in preventing blindness is identifying patients and bringing them to specialty care. Diseases that affect the retina, t…
Within the last few years, cellphone subscriptions have spread widely and now cover even the remotest parts of the planet. Adequate access …
VisionBlocks is an on-demand, in-browser, customizable, computer-vision application-building platform for the masses. Even without any prio…
We have developed a camera system that captures movies at an effective rate of approximately one trillion frames per second. In one frame o…
We demonstrate a new technique that allows a camera to rapidly acquire reflectance properties of objects "in the wild" from a single viewpo…
We have created a 3D motion-tracking system with automatic, real-time vibrotactile feedback and an assembly of photo-sensors, infrared proj…
We present a near-real-time system for interactively exploring a collectively captured moment without explicit 3D reconstruction. Our syste…
With networked cameras in everyone's pockets, we are exploring the practical and creative possibilities of public imaging. LensChat allows …
Can a person look at a portable display, click on a few buttons, and recover his or her refractive condition? Our optometry solution combin…
This work focuses on bringing powerful concepts from wave optics to the creation of new algorithms and applications for computer vision and…
We present a new method for scanning 3D objects through a single-shot, shadow-based method. We decouple 3D occluders from 4D illumination u…
Computational photography is an emerging multi-disciplinary field at the intersection of optics, signal processing, computer graphics and v…
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…
Is it possible to create passive displays that respond to changes in viewpoint and incident light conditions? Holograms and 4D displays res…