Researchers from American technology company NVIDIA have developed a deep learning method that can reconstruct damaged, corrupted, or partially-erased photos with realistic results.
The method performs a process called “image inpainting” that can also be used in photo editing software to remove unwanted objects and fill those areas with realistic computer-generated alternatives, similar to what Photoshop’s Content-Aware tool does.
But unlike Photoshop’s Content-Aware tool, NVIDIA’s A.I. doesn’t obtain information from surrounding pixels to fill the gaps, it actually understands what the object should look like. Check out the examples below.
1.
2.
3.
4.
NVIDIA A.I. vs. Adobe Content Aware
Watch the A.I. in action below
What do you think of NVIDIA’s new technology? Share this post with a designer friend and voice your views in the comments below.