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.
Pixel-level change detection pseudo-label learn- ing for remote sensing change captioning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 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.