Metraipolis › archive › dc_48ec12496fd3

Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing — arXiv:2608.03023

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03023
License (as archived)
CC0-1.0
Archived
2026-10-31T12:18:27.239Z
SHA-256 of the archived text
c710393057ad9229dc9966771f1af9ef984b0bf666fe1e0357f652667d95e840
Stable URL of this page
https://metraipolis.com/documento/dc_48ec12496fd3

How to cite

Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing — arXiv:2608.03023 — arXiv (en), https://arxiv.org/abs/2608.03023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48ec12496fd3 (Metraipolis archive dc_48ec12496fd3, sha256 c710393057ad9229dc9966771f1af9ef984b0bf666fe1e0357f652667d95e840)
BibTeX
@misc{dc48ec12496fd3,
  title = {Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing — arXiv:2608.03023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48ec12496fd3; sha256 c710393057ad9229dc9966771f1af9ef984b0bf666fe1e0357f652667d95e840},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Remote sensing semantic segmentation is hindered by costly pixel-level annotations, motivating training-free open-vocabulary methods. Recently, the recent release of DINOv3 brings this http URL , which equips the standalone DINO backbone with image-text contrastive learning and thus opens up the possibility of open-vocabulary segmentation. We propose DinoSplat-OV, a training-free framework that adapts DINOv3 to remote sensing without fine-tuning or additional pretraining. Targeting the dense distribution, multi-scale nature, and large size of remote sensing imagery, we design two core modules. Its Text-aware Laplacian Propagation module de-noises patch-level predictions by combining textual semantic affinities with local visual similarity, improving regional consistency while preserving boundaries. Its Gaussian Splatting Upsampling module reconstructs pixel-level features through RGB-guided anisotropic aggregation and test-time optimization. A global-anchor sliding-window strategy further supports large-scale imagery. Experiments on UDD5, DOTA, and LoveDA demonstrate competitive or superior performance over existing training-free methods, effectively filling the gap of DINO-series models in training-free open-vocabulary segmentation and providing a viable new path for further advances in this direction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03023 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.979Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).