It takes two to make a good picture, one in front and one behind the camera. And a photographer with a creative eye, so no, I don’t believe photographers will completely replace by machines. However, taking a photo in poor lighting can often result in something too pixelated and noisy to be useful. Then a smart service that "clean" the image from noise is an excellent service and can also be widely used for satellite images, astronomy and within medical applications... This program could help to bring old images in line with modern quality standards. But what happens when we use the AI to removing watermarks and other copyright marks from artwork.
Last week at the Thirty-fifth International Conference on Machine Learning (ICML) in Stockholm, a team of NVIDIA researchers, in partnership with researchers from Aalto University and Massachusetts Institute of Technology (MIT), shared details of a new artificial intelligence (AI) program that can remove grain from images with a extraordinary accuracy.
What's incredible about this particular AI is its ability to know what a clean image looks like without ever actually seeing a noise-free image. Rather than training the deep-learning network by giving it a noisy image and a clean image to learn how to make up the difference, NVIDIA's AI is trained using two images with different noise patterns.
