{Disarmed} This new Google method transforms pixelated photos into spectacular high-resolution images
If one thing is getting better at artificial intelligence, it is image generation. Based on an initial model, current artificial intelligences can generate a similar image , color or scale at higher resolution . The latter is something that Google's AI does very well, so much so that it converts fully pixelated photos into high-resolution photos .
Recent research by Google's artificial intelligence department shows how new advances in this area allow creating incredible images. The company's machine learning model is capable of taking a photo with little resolution and scaling it to achieve unique details.
Diffusion models
When it comes to climbing photographs by artificial intelligence, there are different methods to achieve this. The one used by Google is one called broadcast models. It is a generative model that began to be implemented in 2015 but it was only recently that this approach has been useful for Google.
As they explain, the system takes as input a low resolution image and from there builds a high resolution image on its own. For this, Google says that they have first trained the AI to lower the resolution of the images and make them extremely pixelated . From there "learn to reverse this process, starting with pure noise and progressively removing noise to achieve a target distribution through the guidance of the low-resolution input image."
With this method Google manages to improve especially the portraits of people. However, it goes a step further and with a second AI it is able to scale the photographs even more. With resolutions of 32 x 32 px it is capable of reaching up to 1024 x 1024 px . For this, first transform them to 64 x 64 px and take that new photograph as a reference to upload to 128 x 128 px, then the process again and so on until the desired resolution.
The results are undoubtedly spectacular, allowing you to create genuinely detailed photos from practically nothing . Although there are some minimal errors (for example when generating the transparencies of the glasses), the photographs can pass as real without any problem. In fact, if the context is not known, an ordinary person would probably not identify that they are scaled by an AI.
In xiaomist.com One of the most spectacular applications of AI in all its glory: this is how videos over 100 years old look like recorded nowThe use of this? Indeed, improving photographs taken by users is a straightforward and clear application for this. For example, to improve the resolution of photos taken with mobile cameras, which are not always the best. However, it can also be useful in other sectors such as medicine to improve medical photographs.
Via | Business Insider
More information | Google AI Blog
-
The news This new Google method transforms pixelated photos into spectacular high resolution images was originally published in xiaomist.com by Cristian Rus .
Comments
Post a Comment