In many regression problems, data on the dependent variable are censored; that is, the values of some observations are known only to be above or else below some value. Such data often arise in ...

Open vocabulary recognition and classification are crucial for a comprehensive understanding of real-world 3D scenes.

However, effectively integrating semantic understanding into 3DGS in a generalizable way remains a challenge. To overcome these bottlenecks, we introduce SceneSplat, the first end-to-end large-scale ...