aiqbench analysis
This research introduces DinoSplat-OV, a training-free framework leveraging DINOv3's image-text contrastive learning capabilities specifically for remote sensing semantic segmentation. By eliminating the need for costly pixel-level annotations through novel modules like Text-aware Laplacian Propagation and Gaussian Splatting Upsampling, it offers an efficient path to open-vocabulary analysis in dense imagery datasets such as UDD5 and DOTA.
Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing
arXiv:2608.03023v1 Announce Type: cross Abstract: Remote sensing semantic segmentation is hindered by costly pixel-level annotations, motivating training-free open-vocabulary methods. Recently, the recent release of DINOv3 brings DINO.txt, 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.
Abstract: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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2608.03023 [cs.CV]
(or arXiv:2608.03023v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.03023 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 262 words
Related coverage
ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation
arXiv · Jun 16, 2026
ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3
arXiv · Sep 30, 2026
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation
arXiv · Sep 30, 2026
Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers
arXiv · Oct 2, 2026