A new AI system developed by researchers at Stanford University demonstrates the ability to generate realistic 3D models from simple 2D sketches in real-time. The technology, named ‘Sketch3D’, uses a novel neural network architecture that interprets the rough outlines and shading of a hand-drawn sketch to predict and render a complete three-dimensional object. The researchers report that the system can produce models suitable for video games, animation, and initial prototyping stages within seconds, significantly accelerating the creative workflow. While currently trained on a specific dataset of common objects, the team indicates that the approach could be expanded to more complex and customized designs in the future. For the full details on the methodology and potential applications, read the complete article at https://technologyreview.com/2024/05/15/sketch3d-ai-model.