An online tool has been unveiled which is capable of bringing black and white photographs to life instantaneously by adding colour to them using artificial intelligence.
Colourisation of old images is a normally time consuming process which requires specialist training and expensive software.
The tool, ColouriseSG, is able to do it for free from only a single digital image and works on iconic historical photographs and old family portraits.
Try it for yourself here or via the interactive tool below.
‹ Slide me ›
Charlie Chaplin in a scene from 'The Gold Rush', 1925. The actor die in 1977 but was one of the greatest performers and entertainers of his generation
‹ Slide me ›
Albert Einstein (1879-1955). The image was taken at Princeton University in 1951, shortly before his death. he is considered to be one of the best scientists of all time and won the Nobel prize for his work on the photoelectric effect and also discovered the elegant equation E=MC^2
‹ Slide me ›
Sir Winston Churchill making the famed 'V' for 'Victory' sign. He is shown in the uniform of the Royal Auxiliary Airforce. The image was converted to colour by the ColouriseSG software
‹ Slide me ›
London, England: Big Ben and the Houses of Parliament from across the Thames in London. The black and white image was instantly converted to colour using the free tool
‹ Slide me ›
As pedestrians watch, an American sailor passionately kisses a white-uniformed nurse in Times Square to celebrate the long awaited-victory over Japan. August 14, 1945. This is an outtake that is not the iconic image
‹ Slide me ›
Migrant Mother image taken by Dorothea Lange. The woman lived between 1895 and 1964 and was snapped on silver print in 1936
It is trained on a back catalogue of old images and uses machine learning to guess what it thinks the image would have looked like in colour.
'The purpose of colourisation is to generate an image with colours that are plausible,' the tool's developers claim.
'It by no means guarantees that the colourised image is an accurate representation of the actual snapshot in time.'
It is also more adept at colourising images of human subjects with natural landscape and can struggle with more complex pictures.
The free-to-use tool was developed to provide an accurate way for people from Singapore to edit their monochrome images.
Existing software, such as Algorithmia, are trained using 1.3 million images from ImageNet, a database of photographs developed in the US by researchers at Stanford University and Princeton University.
The idea of ColouriseSG was to provide a large enough data-set to be relevant to the residents of Singapore.
Tech firm NVIDIA have released several different