Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

This project aims to develop an object detection system for architectural floor plans using the YOLOv8 model. The system was trained to detect various elements commonly found in floor plans, such as ...