Nvidia debuted a deep learning method that can edit or reconstruct an image that is missing pixels or has holes via a process called “image inpainting.” The model can handle holes of “any shape, size, location or distance from image borders,” and could be integrated in photo editing software to remove undesirable imagery and replace it with a realistic digital image – instantly and with great accuracy. Previous AI-based approaches focused on rectangular regions in the image’s center and required post processing. Continue reading Nvidia’s New AI Method Can Reconstruct an Image in Seconds

Harvard University researchers have programmed a robot swarm of more than 1,000 bots that can self-assemble into two-dimensional shapes. The “Kilobots” are roughly the size of a penny, and cost $14 in parts. It takes only a few minutes to put a Kilobot together. In order to program them at the same time, the roboticists use an infrared light from an overhead controller, which gives instructions. Infrared signals also help the robots communicate with each other to create formations. Continue reading Harvard University Researchers Create Biggest Kilobot Swarm