Researchers at Nvidia have developed an unsupervised learning method for computers, which enables them to make changes in video content. Using this technique, the researchers were able to produce some amazing results.
Earlier, AI tools required massive amounts of data in order to process comparison between the content. However, based on automated learning, it was quite difficult to train the machines to find their own patterns. For example, super-resolution can be considered as a problem of mapping a low-resolution image to a corresponding high-resolution image; colorization can be considered as a problem of mapping a gray-scale image to a corresponding color image. Today, the machines are using the new algorithms that are quite efficient, especially in applying weather effects such as mapping sunny days to rainy ones and creating the equivalent of a “snow plow” filter for videos. The color effects used by AI makes the video appealing and real. While humankind is already getting ready to face the threat from AI-based robots stealing our jobs, some researchers believe that Nvidia’s recent work in the field of AI only shows how technology has advanced giving AI the ability to create an illusion of a real and fake world, that could cause worry for humanity.
— Oli Franklin-Wallis (@olifranklin) December 4, 2017 You can read the research paper in full here. The researchers are expected to present their work this week at the NIPS AI conference in Long Beach, California.
