HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering
This enables complex operations on dense urban 3D scenes and digital twins, representing an incremental advance by extending existing techniques to a larger scale.
The paper tackles the problem of scaling open-vocabulary 3D scene understanding to city-scale point clouds, achieving this by applying a superpoint graph clustering approach to the SensatUrban dataset with a synthetic labeling pipeline that eliminates hand-annotation.
Traditional 3D scene understanding techniques are generally predicated on hand-annotated label sets, but in recent years a new class of open-vocabulary 3D scene understanding techniques has emerged. Despite the success of this paradigm on small scenes, existing approaches cannot scale efficiently to city-scale 3D datasets. In this paper, we present Hierarchical vocab-Agnostic Expert Clustering (HAEC), after the latin word for 'these', a superpoint graph clustering based approach which utilizes a novel mixture of experts graph transformer for its backbone. We administer this highly scalable approach to the first application of open-vocabulary scene understanding on the SensatUrban city-scale dataset. We also demonstrate a synthetic labeling pipeline which is derived entirely from the raw point clouds with no hand-annotation. Our technique can help unlock complex operations on dense urban 3D scenes and open a new path forward in the processing of digital twins.