Abstract: Deep learning has entirely transformed the way real-time object detection works. Though, one feature that hasn't been fully discovered is the role of shape descriptorstools that were ...

Abstract: In LiDAR-based 3D object detection, severe occlusion often leads to incomplete object shape in point cloud scene. It is a critical challenge as it will significantly degrade detection ...

Rex-Omni is a 3B-parameter Multimodal Large Language Model (MLLM) that redefines object detection and a wide range of other visual perception tasks as a simple next-token prediction problem.

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.