UniSplat is a feed-forward reconstruction framework in autonomous driving scenarios. Unlike traditional methods that require dense, overlapping views and per-scene optimization, UniSplat achieves ...

Abstract: While conventional lossy compression methods predominantly depend on autoencoders to map point clouds into latent representations, they often neglect the intrinsic redundancy within these ...

In this work, we introduce DINOv, a Visual In-Context Prompting framework for referring and generic segmentation tasks. For visualization and demos, we also recommend trying T-Rex demo link, which is ...

Abstract: The problem of time-dependent nonlinear equality-constraint programming (TDNECP) is a hot topic in various scientific and engineering fields. In this paper, the problem-solving of TDNECP is ...