DinoSplat-OV does training-free open-vocabulary segmentation on remote sensing images by combining DINOv3 features with Laplacian smoothing and Gaussian-splatting upsampling, reaching 42.9 mIoU on UDD5 and 37.5 average on four datasets.
LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing
DinoSplat-OV does training-free open-vocabulary segmentation on remote sensing images by combining DINOv3 features with Laplacian smoothing and Gaussian-splatting upsampling, reaching 42.9 mIoU on UDD5 and 37.5 average on four datasets.