Abstract: To address the challenges of low detection accuracy in optical remote sensing images (RSIs) caused by densely distributed targets, extreme scale variations, and insufficient feature ...
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 ...
Abstract: Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a ...
Training AI world models on data about physical environments could improve their real-world capabilities in technologies such ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results