Open-Vocabulary Remote Sensing Image Segmentation

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

TerraMesh-Masks: Open-Vocabulary Segmentation for Earth Observation
Nov 5, 2026Benedikt Blumenstiel, Hugues Devimeux, Johannes Jakubik +1Open-Vocabulary Remote Sensing Image Segmentation Open-Vocabulary Semantic Segmentation
ETH Zurich Zurich, Switzerland
OpenEarth-OVS44: A Multimodal Remote Sensing Dataset for Open-Vocabulary Segmentation
Oct 21, 2026Yimin Wei, Hongruixuan Chen, Hao Zheng +5Open-Vocabulary Remote Sensing Image Segmentation Remote Sensing Image Segmentation
The University of Tokyo · RIKEN AIP · East China Normal University +1
GeoSeg-OV: Bridging Geospatial Gaps with Structural Guidance for Open-Vocabulary Remote Sensing Segmentation
Aug 11, 2026Ruizhong Liu, Tingzhang Luo, Zaiyan Zhang +4Remote Sensing Image Segmentation Open-Vocabulary Remote Sensing Image Segmentation
School of Computer Science, China University of Geosciences, Wuhan 430074, Hubei, China · Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, Guangdong, China · Department of Computer Science, City University of Hong Kong, Hong Kong, China +3
Prompt-Calibrated SAM 3 for Open-Vocabulary Remote Sensing Semantic Segmentation
Jun 20, 2026Yanghui Song, Nanqing Liu, Haonan Yin +3Remote Sensing Image Segmentation Promptable Image Segmentation
School of Information Science and Technology, Yunnan Normal University, Kunming, China · School of Computer Science and Engineering, Beihang University, Beijing, China · College of Computer Science, Beijing University of Technology, Beijing, China
DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery
May 4, 2026Ryan Faulkenberry, Saurabh PrasadImage Segmentation Remote Sensing Image Segmentation
University of Houston
Perturbation-Regularized Open-Vocabulary Remote Sensing Segmentation with Unified Multi-Domain Evaluation
Apr 17, 2026Bingyu Li, Tao Huo, Haocheng Dong +4Image Segmentation Remote Sensing Image Segmentation
Department of Electronic Engineering and Information Science, University of Science and Technology of China, China · Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China · School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, China
Decouple and Rectify: Semantics-Preserving Structural Enhancement for Open-Vocabulary Remote Sensing Segmentation
Apr 2, 2026Jie Feng, Fengze Li, Junpeng Zhang +4Open-Vocabulary Remote Sensing Image Segmentation Remote Sensing Image Segmentation
Xidian University China · Jimei University China · South China University of Technology China
ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation
Mar 31, 2026Wenyang Chen, Zhanxuan Hu, Yaping Zhang +2Open-Vocabulary Remote Sensing Image Segmentation Image Segmentation
Yunnan Normal University · Xi’an University of Posts & Telecommunications

Nov 5, 2026J/K move · Enter open · S save

TerraMesh-Masks: Open-Vocabulary Segmentation for Earth Observation

Benedikt Blumenstiel, Hugues Devimeux, Johannes Jakubik, Konrad Schindler

ETH Zurich Zurich, Switzerland

Open-Vocabulary Remote Sensing Image Segmentation Open-Vocabulary Semantic Segmentation Remote Sensing Image Segmentation Remote Sensing Benchmarks

Open paper AskPDF arXiv

Open-vocabulary segmentation (OVS) enables models to segment a variety of concepts specified in natural language, removing the need for fixed label sets and fine-tuning. While recent OVS approaches have shown strong performance on natural images, they transfer poorly to Earth observation (EO) data due to differing semantics, scales, sensing modality, and geographic context. To date, large-scale EO-specific datasets and benchmarks for OVS remain scarce. We, therefore, introduce TerraMesh-Masks, a large-scale open-vocabulary segmentation dataset for EO, comprising 16 million binary masks aligned with nine million multimodal TerraMesh samples and annotated using OpenStreetMap and Overture-derived semantics. In addition, we provide an expert-reviewed evaluation set of 523 samples covering over 200 classes to enable robust evaluation. To demonstrate the impact of TerraMesh-Masks, we build an open-vocabulary version of TerraMind. Our results demonstrate significantly improved performance over general-purpose state-of-the-art models reaching 35.18% IoU versus 16.29% for DINOv3.txt and 11.33% for SAM-3. We release the dataset publicly under a permissive license at https://huggingface.co/datasets/ibm-esa-geospatial/TerraMesh-Masks.