I work at ValueFirst Digital Media Private Ltd. I am a Product Marketer in the Surbo Team. Surbo is Chatbot Generator Platform owned by Value First. ...Full Bio
I work at ValueFirst Digital Media Private Ltd. I am a Product Marketer in the Surbo Team. Surbo is Chatbot Generator Platform owned by Value First.
Success story of Haptik
1012 days ago
Who is afraid of automation?
1012 days ago
What's happening in AI, Blockchain & IoT
1013 days ago
3 million at risk from the rise of robots
1013 days ago
Artificial Intelligence Timeline: Infographic
This AI bot from Microsoft can sketch from text descriptions
Microsoft is working on an AI enabled bot that can create
images from the text descriptions of an object.
This technology can generate images of everything according to Microsoft. Whether it is an ordinary pastoral scene like grazing livestock or an absurd floating double decker bus.
If you look at the images produced you will find details that have not been mentioned in the description indicating that this AI has an artificial imagination.
The technology under development in Microsoft's research labs is programmed to pay close attention to individual words when generating images from caption-like text descriptions, the company said.
This deliberate focus produces a nearly three-fold boost in image quality compared to the previous state-of-the-art technique for text-to-image generation, according to results on an industry standard test reported in a research paper posted on arXiv.org.
"If you go to Bing and you search for a bird, you get a bird picture. But here, the pictures are created by the computer, pixel by pixel, from scratch," said Xiaodong He, a principal researcher at Microsoft's research lab in Washington.
He and colleagues started with technology
that automatically writes photo captions - the CaptionBot - and then moved to
the one that answers questions humans ask about images, such as the location or
attributes of objects, which can be especially helpful for blind people
Qiuyuan Huang, a postdoctoral
researcher now wishes to use the text to generate the image.
This text to image generation technology could find practical appliactions in the form of a sketch assistant to interior designers & painters or as a tool for voice-controlled photo refinement, as per researchers.
At the core of this bot is technology known as Generative Adversarial Network (GAN).
The network comprises of two machine learning models. There is one that generates the images from the text descriptions and another one called discriminator that makes use of text descriptions to judge the authenticity of the result.