Researchers including one of the Indian origin have developed an AI artificial intelligence tool. The AI tool can turn the blurry and unrecognizable image of a person into a perfect computer-generated portrait. AI is the latest technology used to detect automatic background scenes and make your picture beautiful. The recently launched technology makes your image attractive.
In this method, it searches through the AI-generated examples of high-resolution images that look similar to the input image, when compressed.
Sachit Menon, the co-author from the Duke University in the US said, as quoted, “While the researchers focused on faces as a proof of concept, the same technique could, in theory, take low-res shots of almost anything and create sharp, realistic-looking pictures, with applications ranging from medicine and microscopy to astronomy and satellite imagery“.
In the previous method, the image of the face was scaled to around 8 times its original resolution. But this time researchers have come up with a different technique which makes image realistic looking face up to 64 of the resolution. It is capable of generating an image that does not exist but it looks real. In the technique faces looking sharper and original.
The Researchers will present their method, called PULSE, at the 2020 conference on Computer Vision and Pattern Recognition(CVPR), held virtually from June 14 to June 19.
Traditional approaches take a low-resolution image and guess what extra pixels are needed by trying to get them to match, on average, with correspondence pixels in high-resolution images the computer has seen before. The system can convert 16 X 16 pixel images of a face to 1024 X 1024 pixels in few seconds. Now the system explores the AI-generated examples of high-resolution faces, instead of taking low-resolution images.