A multi-scale Transformer with semantic-NeRF supervision improves absolute pose regression on TartanAir over prior APR baselines, though the evaluation protocol is under-specified.
Geometry-aware learning of maps for camera localization
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Robust Visual Localization via Semantic-Guided Multi-Scale Transformer
A multi-scale Transformer with semantic-NeRF supervision improves absolute pose regression on TartanAir over prior APR baselines, though the evaluation protocol is under-specified.