Abstract: In this article, we address the challenge of multiobject tracking (MOT) in moving uncrewed aerial vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left ...

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike ...

Deep learning techniques have transformed the estimation of homographies in computer vision, enabling robust and accurate alignment of images across a wide range of conditions. These methods replace ...

Estimating the homography matrix between images captured under radically different camera poses and zoom factors is a complex challenge. Traditional methods rely on the R...Show More Estimating the ...