LiteLoc creates a compact color-free Gaussian feature representation and condenses dense matches to 5% for 19x faster PnP solving, outperforming STDLoc in efficiency with negligible accuracy loss.
Crossfire: Camera relocalization on self-supervised features from an implicit representation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
LiteLoc creates a compact color-free Gaussian feature representation and condenses dense matches to 5% for 19x faster PnP solving, outperforming STDLoc in efficiency with negligible accuracy loss.