A Gaussian splatting framework with per-point semantic features, SAM2 boundary pseudo-labels, and two aggregation losses gives fast, view-consistent multi-view segmentation for remote sensing under sparse labels.
Bifa: Remote sensing image change detec- tion with bitemporal feature alignment,
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
-
Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
A Gaussian splatting framework with per-point semantic features, SAM2 boundary pseudo-labels, and two aggregation losses gives fast, view-consistent multi-view segmentation for remote sensing under sparse labels.