Interesting Engineering | July 18, 2026
Creating a realistic 3D model from a simple image remains surprisingly difficult for artificial intelligence. While AI can generate impressive pictures, producing the precise CAD code engineers use to design aircraft parts, cars, and consumer products is far more challenging. Even a small mistake can make a design unusable. Now, researchers from MIT, IBM, and Red Hat have developed a framework that significantly improves the ability of AI systems to turn 2D images into functional CAD programs, producing more accurate designs while reducing inference computation by about 80 percent. The team's framework, called Geometric Inference Feedback Tuning (GIFT), works with vision-language models that convert a 2D image and text description into Python code that can be executed in CAD software to create a 3D object. GIFT asks the model to solve the same CAD problem multiple times in parallel. Some outputs are correct, some are close to the target design, and others are much further away. The researchers say these near-misses are the most valuable because they reveal exactly what the model does not yet understand. The system executes each generated CAD program and compares the resulting 3D geometry with the target using Intersection over Union (IoU). Rather than discarding imperfect outputs, GIFT identifies those that are close to correct and uses them to generate new training examples.