[Recommended resolution: 1080p]
To appear in SIGGRAPH 2014.
Abstract:
Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-specific, local retouching that a professional photographer typically applies to generate such portraits.

We introduce a technique to transfer the style of an example headshot photo onto a new one. This can allow one to easily reproduce the look of renowned artists. At the core of our approach is a new multiscale technique to robustly transfer the local statistics of an example portrait onto a new one. This technique matches properties such as the local contrast and the overall lighting direction while being tolerant to the unavoidable differences between the faces of two different people. Additionally, because artists sometimes produce entire headshot…

На пути к искусственному интеллекту.

Watch as scientists replace genes in goats to create an impenetrable silk skin. | For more Futurescape, visit http://science.discovery.com/tv-shows/futurescape/#mkcpgn=ytsci1

Subscribe to Science Channel! | http://www.youtube.com/subscription_center?add_user=sciencechannel

James Woods discusses bionic limbs, immortality and other future tech! | http://bit.ly/jameswoodsinterview

Police in Finland use human blood from a mosquito caught inside a stolen car to identify a suspect in the theft.

http://www.expost.space/jller (cz) http://www.prokopbartonicek.com (en) http://www.allesblinkt.com (en)  Jller is part of an ongoing research project in the…

This machine sorts candy by color. It separates different colored Skittles and M&Ms pieces and puts them into individual cups.

Project details: http://beta.ivc.no/wiki/index.php/Skittles_M%26M%27s_Sorting_Machine

The machine is fully autonomous and will sort an entire 1.5kg/56oz bag in approx. 5 minutes. It is made of an AVR microcontroller (Arduino Uno), color sensor, distance sensor, servo actuators, plastic frame tubes and a few custom 3D printed parts.

The system processing is based around pseudo-realtime programming which helps keep all the parts of the system up to date and keep the system running smoothly. Each process is designed around the notion of event driven finite-state machine (FSM) execution.

Controller: ATmega328 (Arduino Uno platform)
Color sensor: ADJD-S311-CR999 CMOS color sensor
Distance sensor: QRE1113 IR sensor
Servos: GWS S35-STD, GWS S125-1T-2BB

Music: Bartlebeats - Tall Bird