Event
Proposing the CoGaussian open-vocabulary collaborative occupancy prediction framework
1 reports · 1 sources
Om Shivam Verma and other researchers propose CoGaussian, an open-vocabulary collaborative semantic occupancy prediction framework that uses sparse 3D Gaussian representations aligned with foundation models to represent scenes, transmits and fuses geometric and semantic information among multiple agents, and no longer relies on dense 3D voxel annotations nor is limited to predefined semantic categories. On the Semantic-OPV2V benchmark, this method surpasses existing open-vocabulary single-agent methods.
Report timeline
- CoGaussian: A Gaussian-based open-vocabulary collaborative 3D scene understanding framework
CoGaussian proposes an open-vocabulary collaborative semantic occupancy prediction framework that uses sparse 3D Gaussians aligned with foundation models to represent scenes as a compact representation for transmitting and fusing geometric and semantic information among multiple agents, no longer relying on dense 3D voxel annotations and no longer limited to predefined semantic categories. On the Semantic-OPV2V benchmark, the method outperforms existing open-vocabulary single-agent approaches.
arXiv cs.RO ·