UW News

Ira Kemelmacher-Shlizerman


July 11, 2022

ClearBuds: First wireless earbuds that clear up calls using deep learning

A hand holding up a 3D printed earbud

UW researchers created ClearBuds, earbuds that enhance the speaker’s voice and reduce background noise.


June 11, 2019

Behind the magic: Making moving photos a reality

Picasso's "Niña con corona y barco" steps out of the frame

UW researchers have figured out how to take a person from a 2D photo or a work of art and make them run, walk or jump out of the frame. The system also allows users to view the animation in three dimensions using augmented reality tools.


January 8, 2018

UW Reality Lab launches with $6M from tech companies to advance augmented and virtual reality research

The UW Reality Lab is launching with $6 million from Facebook, Google, and Huawei to accelerate innovation in augmented and virtual reality and educate the next generation of researchers and practitioners.


July 11, 2017

Lip-syncing Obama: New tools turn audio clips into realistic video

Reel of Obama photos

A new machine learning tool developed by UW computer vision researchers can create realistic videos from audio files alone – including speeches by President Barack Obama.


July 21, 2016

Imaging software predicts how you look with different hair styles, colors, appearances

A personalized image search engine developed by a University of Washington researcher lets a person imagine how they would look a with different a hairstyle, if they lived in a different time period or any other appearance change that can be synthesized with internet photos.


June 23, 2016

How well do facial recognition algorithms cope with a million strangers?

photo of images in MegaFace gallery

University of Washington computer scientists have launched the “MegaFace Challenge,” the world’s first competition aimed at evaluating and improving the performance of face recognition algorithms at the million person scale.


December 7, 2015

What makes Tom Hanks look like Tom Hanks?

UW researchers have reconstructed 3-D models of celebrities such as Tom Hanks from large Internet photo collections. The model can deliver speeches that the real actor never performed – one step toward developing fully interactive digital personas of people from family or historic photo collections.


April 9, 2014

Automated age-progression software lets you see how a child will age

A single photo of a child (far left) is age progressed (left in each pair) and compared to actual photos of the same person at the corresponding age (right in each pair).

University of Washington engineers have developed software that automatically generates images of a young child’s face as it ages through a lifetime. The technique is the first fully automated approach for aging babies to adults that works with variable lighting, expressions and poses.