New AI Imaging Technique Reconstructs Photos with Realistic Results

New AI Imaging Technique Reconstructs Photos with Realistic Results

  • April 23, 2018
Table of Contents

New AI Imaging Technique Reconstructs Photos with Realistic Results

To prepare to train their neural network, the team first generated 55,116 masks of random streaks and holes of arbitrary shapes and sizes for training. They also generated nearly 25,000 for testing. These were further categorized into six categories based on sizes relative to the input image, in order to improve reconstruction accuracy.

Source: nvidia.com

Tags :
Share :
comments powered by Disqus

Related Posts

The AI Revolution Hasn’t Happened Yet

The AI Revolution Hasn’t Happened Yet

Artificial Intelligence (AI) is the mantra of the current era. The phrase is intoned by technologists, academicians, journalists and venture capitalists alike. As with many phrases that cross over from technical academic fields into general circulation, there is significant misunderstanding accompanying the use of the phrase.

Read More
A Face-Detection Library in 200 Lines of JavaScript

A Face-Detection Library in 200 Lines of JavaScript

The pico.js library is a JavaScript implementation of the method described in 2013 by Markuš et al. in a technical report. The reference implementation is written in C and available on GitHub: https://github.com/nenadmarkus/pico.

Read More
China’s tech giants are venturing into autonomous driving

China’s tech giants are venturing into autonomous driving

If there’s one thing China’s tech giants are known for, it’s their ability to venture into everything from social media, to online payments, to delivery services. The latest thing they’re all speeding towards? Autonomous driving.

Read More