Author name: Lingjun Zhao, Yandong Luo, James Hays, Lu Gan

arXiv:2512.03370v3 Announce Type: replace
Abstract: We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have dem…

arXiv:2512.03370v2 Announce Type: replace
Abstract: We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have dem…