LoopGNN uses graph attention over clusters of visually similar keyframes to improve loop closure precision and recall, outperforming pairwise baselines on off-road and campus datasets.
Language-grounded dynamic scene graphs for interactive object search with mobile manipulation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Visual Loop Closure Detection Through Deep Graph Consensus
LoopGNN uses graph attention over clusters of visually similar keyframes to improve loop closure precision and recall, outperforming pairwise baselines on off-road and campus datasets.