Computer Vision News - August 2016

In this section, Computer Vision News lists some of the great stories that we have just found somewhere else. We share them with you, generally with a short comment. Enjoy! Imaging Software Lets You Try all Kind of New Hairstyles Ever wondered what you would look like in another place, another time or simply with another color? See by yourself with Dreambit , a new personalized image search engine developed by a University of Washington computer vision researcher. The software’s algorithms mine Internet photo collections for images in the category of your choice and seamlessly map your face onto the results. Read... Computer Vision News Spotlight News 11 1st Eastern European Computer Vision Conference a Success Before you ask, we need to update you about the meeting in Odessa : with more than 500 applicants and 150 selected attendees, the first EECVC was a success. Debates were rich, involvement was very high and we only heard very positive feedback. Good job! Hungarian Inventor of the “Kálmán Filter” Passed Away Scientist Rudolf Kálmán, the legendary Hungarian-born inventor of the so-called “ Kálmán filter ”, a mathematical technique widely used in the digital computers of control systems, navigation systems, avionics, and outer-space vehicles, died last month. His invention was used during the Apollo program as well as in the NASA Space Shuttle . Read… BMW Tests Autonomous Driving Systems - at the Olympics! For the past six years, BMW has been the official mobility partner of the U.S. Olympic Committee . Besides the honor coming with the role, the automaker has also created a customized motion tracking system for the USA Swimming team , treating American swimmers like they’re autonomous cars in a swimming pool. Read… Neural networks Turn Face Sketches into Photos Transforming artwork into pictures, like a reverse process of Prisma : a team of four neuroscientists at Radboud University will present a model at the upcoming ECCV for inverting face sketches to synthesize photorealistic face images by using deep neural networks . To train and test the algorithm, the scientists used computer-generated sketches based on the more than 200,000 celebrity images in the CelebA dataset. Read…