VAFS replaces per-frame embedding in dense 3D mapping with per-object synthetic view embedding, using simulator ground-truth segmentation, achieving faster and higher-IoU semantic maps in simulation.
Xia, Brian Ichter, Kanishka Rao, Keerthana Gopalakrishnan, Michael S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Voxel-Aggregated Feature Synthesis: Efficient Dense Mapping for Simulated 3D Reasoning
VAFS replaces per-frame embedding in dense 3D mapping with per-object synthetic view embedding, using simulator ground-truth segmentation, achieving faster and higher-IoU semantic maps in simulation.