Press Clips from 2016

July 25, 2016


New advance in 3D graphics may make the next Avengers movie look even more realistic

Are you having trouble distinguishing real life objects from digital creations in the latest movies and TV shows? Well, things are only going to get harder to determine from here on out, thanks to a new method discovered by a group of researchers. In short, they've figured out how to improve the way graphics software can render light as it interacts with extremely small details on the surface of materials. That means you could finally see the metallic glitter in Captain America's shield, the tiny sparkles in the Batmobile's paint job, and super-realistic water animations. Full Story

July 5, 2016


Cubic blog post: a Challenge to Universities

One of the best aspects of working in innovation is spending time at university research laboratories. It is at places like the University of California, San Diego (UC San Diego) Center for Visual Computing that the next generation of basic research is being conducted. Full Story

February 12, 2016


Smart car algorithm sees pedestrians as well as you can

It's one thing for computers to spot people in relatively tame academic situations, but it's another when they're on the road -- you need your car to spot that jaywalker in time to avoid a collision. Thankfully, UC San Diego researchers have made that more realistic than ever. They've crafted a pedestrian detection algorithm that's much quicker and more accurate than existing systems. It can spot people at a rate of 2-4 frames per second, or roughly as well as humans can Full Story

February 12, 2016

Spectrum IEEE

Deep Learning Makes Driverless Cars Better at Spotting Pedestrians

Today's car crash-avoidance systems and experimental driverless cars rely on radar and other sensors to detect pedestrians on the road. The next improvement may come from engineers at the University of California, San Diego (UCSD), who have developed a pedestrian detection system that can perform in close to real-time based on visual cues alone. This video-only detection could make systems for spotting pedestrians both cheaper and more effective. Full Story

February 12, 2016

Trend Hunter

Pedestrian Detection Algorithms

A group of engineers and researchers working out of the University of California, San Diego have invented a high-tech pedestrian detection system that is capable of performing pedestrian recognition in a more accurate manner than existing systems. Most pedestrian recognition technologies divide images into smaller sections that are processed in order to determine whether the image represents a human form. This makes things challenging because humans obviously come in different shapes and sizes Full Story