Xiaomi builds DeepExposure AI to restore detail in over/under exposed photos

Smart Android And Trik-Commenting on Andorid indeed never endless, because smart devices this one is often updated every certain amount of time. So that the market can always be garapnya menerinya with pleasure. And it is not denied if this device has become the lifestyle of each society. To not wonder if the 6th business information and many are turning to mobail smartphone. With Android which thoroughly dominated the mobile industry, choosing the best Android smartphone is almost identical to choose the best smartphone, period. But while Android phones have few real opponents on other platforms, internal competition is intense.

From the sleek devices impress with the design premium, up to a full plant furniture features, to a very good device, and affordable mobile phone has a heavy weight, the Android ecosystem inhabited by a diverse range of attractive mobile phone Xiaomi builds DeepExposure AI to restore detail in over/under exposed photos Xiaomi builds DeepExposure AI to restore detail in over/under exposed photos,But "oversize" are subjective, and sometimes pieces of the specification and a list of features is not enough to get an idea of how good a phone. In this roundup, we look at the absolute best-the Android phone you can't go wrong with. The habits of young people or to accentuate trand blindly lifestyle, make this a medoroang this clever device industry vying to do modifications to the device, with a distinctly vitur vitur-tercanggihnya. So it can be received over the counter Xiaomi builds DeepExposure AI to restore detail in over/under exposed photos

Modern smartphone photography is as much a product of what the image sensor captures as it is of what an image processor does with the information afterwards. Xiaomi has presented a paper that aims to solve a common issue of small pixels – limited dynamic range – by employing an AI to fix the exposure of the photo.

But not the whole photo, instead the image is segmented into sub-images and their exposure is adjusted separately. Then the different parts are merged to form the final image.

Take this image for example. The buildings are white, the clouds are white and the overexposed sky is white. The AI, dubbed DeepExposure, does a great job at restoring detail.

The schematic illustration of the algorithm. Firstly, it harnesses image segmentation to obtain sub-images. For different sub-images, it uses different exposures according to the policy network and they are fused together to form the final high-quality image

To teach the AI (based on a Generative adversarial network), the Xiaomi team used the images from the

rel="noopener noreferrer">MIT-Adobe FiveK dataset. It contains unedited RAW photos as well as the same photos retouched by five experts (the team used 3,000 images, picking the ones retouched by Expert C).

The network works on low-resolution images – its goal is to come up with the best parameters for classic image filters. Think of it as the AI fiddling with the dials in Lightroom. This simplifies the learning process, but should also speed up image processing.

Retouched images of different algorithms. From left to right, top to bottom: Original input image, DeepExposure I, DeepExposure II, Exposure, FI, Expert C, DPED, CycleGAN, Deep Photo Enhancer and Deep Guided Filter

Source (PDF) | Via

Let's block ads! (Why?)

Tweet

Subscribe to receive free email updates: