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.
Habitat-matterport 3d semantics dataset
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
SEMNAV trains visual semantic navigation policies on semantic segmentation inputs rather than RGB, reports higher success rates in Habitat 2.0 on HM3D, and shows improved real-world transfer on robotic platforms.
citing papers explorer
-
FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers
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.
-
SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation
SEMNAV trains visual semantic navigation policies on semantic segmentation inputs rather than RGB, reports higher success rates in Habitat 2.0 on HM3D, and shows improved real-world transfer on robotic platforms.