Disney Research has developed an innovative algorithm that generates complex 3D computer models from regular 2D images to meet the needs of video game and filmmakers. To be more specific, it requires multiple images to capture the scene from a variety of vantage points. Continue reading for a video and more information.
According to Gizmag, “the team used a hundred 21-megapixel photos for each of their demo models. These were captured by moving the camera along a straight line for each shot. Though this approach makes it easier to process the data, the team says that the algorithm can be applied to less regimented sets of images.”