Adobe has released a video that shows off features powered by Adobe Sensei that uses Artificial Intelligence and machine learning. It transforms an ordinary picture into a perfect selfie through a range of editing tools.
“Great portrait photography requires the right perspective, equipment, and editing expertise,” says Adobe. “But what if we can tap into the power of artificial intelligence and deep learning to transform bad portrait shots into good ones – all on a smartphone?”
The software seems to have a trio of AI-powered developments on the forefront of today’s photo software research: 3D-facial mapping, style transfers and automatic portrait masking.
It starts with clicking a selfie and adjusting few sliders including the light, depth of field, head position and few more. Once the transformation is done, user can switch to overall photo style. The interesting feature of this software is that it allows a user to copy the style from the sample picture to your newly clicked selfie. This feature includes lightening styles and coloring which can give pictures a complete new look and feel of any other picture selected.
Additionally, users can also cut and paste the photo styles from one picture to the other. In future, these functions are estimated to be included in certain products of Adobe Creative Cloud range.
According to Digital Trends, as of now, it is not clear how close the program is to reality. Adobe, however, confirmed that the app in the video is not computer-generated. But, it does take the biggest advancements in using Artificial Intelligence to edit pictures from academic research and puts them all into one consumer-oriented app.