3D-LENS formalizes single-view aerial-ground re-identification and uses 3D lifting for novel view synthesis plus bias-mitigating representation learning to achieve SOTA cross-view matching.
IEEE TCSVT34(7), 5589–5602 (2024) 5
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
-
3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification
3D-LENS formalizes single-view aerial-ground re-identification and uses 3D lifting for novel view synthesis plus bias-mitigating representation learning to achieve SOTA cross-view matching.