Summing VPR descriptors of the same place across multiple environmental conditions into one fused descriptor improves recall@1 over single-condition reference sets with no extra matching compute.
Are local features all you need for cross-domain visual place recognition? In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6155--6165, 2023
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition
Summing VPR descriptors of the same place across multiple environmental conditions into one fused descriptor improves recall@1 over single-condition reference sets with no extra matching compute.