A system builds a sparse 3-D graph of objects and their spatial and semantic relations from indoor RGB-D video, then uses it for visual question answering and robot task planning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
A system builds a sparse 3-D graph of objects and their spatial and semantic relations from indoor RGB-D video, then uses it for visual question answering and robot task planning.