Researchers at Facebook have developed computer vision tech, which can provide real-time text translation in AR.
Praveen Krishnan and Tal Hassner, researchers at Facebook, have published their research revealing an artificial intelligence design called TextStyleBrush which can view handwritten or typed words through the smartphone camera, copy its typeface, and then replace the original text with another word virtually in the camera view.
“It works similar to the way style brush tools work in word processors, but for text aesthetics in images. It surpasses state-of-the-art accuracy in both automated tests and user studies for any type of text. Unlike previous approaches, which define specific parameters such as typeface or target style supervision, we take a more holistic training approach and disentangle the content of a text image from all aspects of its appearance of the entire word box. The representation of the overall appearance can then be applied as one-shot-transfer without retraining on the novel source style samples.” – The researchers wrote in a blog.
While the modern applications for mobile AR, especially when compared to abilities implemented by Apple and Google, Facebook also has its vision set on combining TextStyleBruch in its upcoming smart glasses.
Also, TextStyleBrush can utilize its typeface recognition ability to replicate handwriting or typeface specimens and apply them to whole text blocks.
Overall, what this technology innovation indicates is that augmented reality smartglasses system will not only be directed by filters changing the landscapes and faces of what users view through the smartglasses, but users will also have the choice to manipulate the information they view via these smart glasses.
Follow us on LinkedIn
Read other Articles