Abstract: Multispectral object detection, which combines RGB visible light and thermal infrared spectral information, has broad applications in complex environments and varying illumination conditions ...

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.

Abstract: Reliable road object detection is crucial for self-driving cars and intelligent transportation systems. However, vision-only techniques fail in low-visibility conditions such as fog, rain, ...

S3OD is a large-scale fully synthetic dataset for salient object detection and background removal, with 140K high-quality images generated using diffusion models. Our model, trained on large-scale ...