Our Research Methodology
This article is one of 350,000 experiments. We use crowd filtering, big data and AI to identify insights.
Cambridge Consultants Has Developed a New AI to Fix Video in Real-Time
Rain, smoke, dirt, and debris-produced distortion would normally be destructive for any videographer's footage, but global research and development firm Cambridge Consultants is now offering an AI solution to reconstruct damaged or obscured frames in real-time. Dubbed DeepRay, this new program calls to mind Adobe’s distortion-correcting system, but manages to accomplish the same feat but in real-time and with live video.
Cambridge Consultants currently plans on showcasing DeepRay at CES 2019. However, in its current state, the system takes advantage of a machine learning architecture known as generative adversarial network (GAN). Speaking broadly, GAN is a two-part neural network that consists of generators and discriminators. DeepRay features a total of six networks, each with their own team of generators and discriminators, which each analyze footage to remedy damaged frames,
from TrendHunter.com http://bit.ly/2rk21Lx
via IFTTT
No comments:
Post a Comment