A new piece of software developed by American tech company, NVIDIA, uses deep-learning to elevate even the roughest sketches into works of art. The new program, dubbed GauGAN, after famous French impressionist Paul Gaugin, uses a tool called generative adversarial networks (GAN) to interpret simple lines and convert them into hyper-realistic images. Its application could help professionals across a range of disciplines such as architecture and urban planning render images and visualizations faster and with greater accuracy, according to the company. A new piece of software developed by American tech company, NVIDIA, uses deep-learning to elevate even the roughest sketches into works of art. Simple shapes become mountains and lakes with just a stroke of what NVIDIA calls a'smart paintbrush' Artificial intelligence systems rely on neural networks, which try to simulate the way the brain works in order to learn.
While it is impossible to replicate the exact conditions in which the original photo was taken, it is possible to add colour to the photo to help us imagine what the photographer could have seen in that instant. It is incredible -- almost magical -- how a little bit of colour can bring us that much closer to that specific moment in time. And as such, for our hackathon in January, our team decided to build a deep learning colouriser tool trained specifically for old Singaporean photos. If you have old black and white photos and would like to colourise them, you can do so here: Colourise.sg. We do not store any of the photos that you upload to our colouriser application.
These stunning pictures of naval forces preparing for battle during the Second World War have been brought back to life 70 years on. The photographs, which show British, American and Finnish troops off the coasts of Japan and Russia during the war, as well as survivors being transferred between ships, have been colourised by emergency medical technician Jared Enos, from North Kingstown, US. The 19-year-old said he has spent the last year transforming the images from their original black and white state into these fascinating colourful images, which he hopes will give a better insight into the Second World War for younger generations. He said: 'Essentially, it focuses on various nations' navies and or vessels in World War II, including the US Marines, Finnish Coastal Defence and the Royal Navy. 'I colourise to create a stronger, more tangible connection to our past.
Earlier this year I saw a post on Mashable which had some amazing photos from World War Two. They really bring the era to life so I was thinking about how we could automate the process of colourising photos and save a ton of - it can cost up to £3k/minute to colourise video professionally. DockerCon EU was coming up and I really wanted to attend. My idea sounded like the perfect solution to my problem! Enlisting the help of my friend Oli Callaghan, we started writing code.
A series of photographs of British professions at the turn of the century have been expertly re-coloured using the latest editing technology. The pictures date back to 1870 and show staple jobs such as courier, nurse and a school teacher with pupils. Photo colourist Matt Loughrey spent six days painstakingly restoring the pictures to full colour before Dell placed the pictures over their modern day counterparts. A series of photographs of British professions at the turn of the century have been expertly re-coloured using the latest editing technology. Photo colourist Matt Loughrey spent six days painstakingly restoring the pictures to full colour.