FUS3DMaps fuses voxel- and instance-level open-vocabulary layers inside a shared 3D voxel map to improve both layers and enable scalable accurate semantic mapping.
Scannet: Richly-annotated 3d reconstructions of indoor scenes
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
PLAF introduces a 2D pixel-wise language-aligned feature extractor paired with a redundancy-reducing storage scheme that supports accurate open-vocabulary 3D scene understanding.