Abstract: The remote sensing image object detection has advanced significantly; yet, small object detection remains challenging due to their limited size and varying scales. Furthermore, real-world ...

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...

Abstract: In recent years, UAV object tracking has provided technical support across various fields. Most existing work relies on convolutional neural networks (CNNs) or visual transformers. However, ...

SAM 3D Objects is a foundation model that reconstructs full 3D shape geometry, texture, and layout from a single image, excelling in real-world scenarios with occlusion and clutter by using ...

Visit us in Washington, DC and Chantilly, VA to explore hundreds of the world’s most significant objects in aviation and space history. Free timed-entry passes are required for the Museum in DC.