Skip to content
Review

TerraMesh-Masks: Open-Vocabulary Segmentation for Earth Observation

Nov 2026 · 0 citations · 26 references
Computer Science

Abstract

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.

View source

Similar papers

Preprint Oct 2026

OpenEarth-OVS44: A Multimodal Remote Sensing Dataset for Open-Vocabulary Segmentation

In remote sensing, open-vocabulary segmentation is particularly important for flexible and scalable land-cover understanding across diverse regions, as it improves generalization to novel categories without requiring exhaustive pixel-level annotations. Despite its great promise, progress in this area remains largely co...

Yi-Min Wei, Hongruixuan Chen, Hao-Xiang Zheng et al. · 0 citations
Preprint Nov 2026

Puzzle: One Pass Is Not Enough for Open-Vocabulary Remote Sensing Segmentation

Open-vocabulary remote sensing image segmentation (OVRSIS) enables the segmentation of unseen classes without additional annotation or retraining. By analyzing the predictions of existing OVRSIS methods, we find that many misclassified patches coexist with visually similar, correctly classified patches of the same clas...

Wen-Song Xu, Si-Qi Lu, Ji-Bao Yuan et al. · 0 citations
Preprint Nov 2026

EO-Jev: Decision Model for Earth Observation

Earth observation (EO) workflows require selecting among known outcomes, estimating confidence, and processing large volumes of imagery. Generative vision-language models can address these tasks, but autoregressive decoding is computationally costly and their confidence estimates are unreliable. Decision models offer a...

Mohamed Atef Abouelhadid, Diaa Addeen Abuhani, Muhammad Akhtar Munir et al. · 1 citation
Review Sep 2026

Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing

While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability and expert interaction, they are either too expensive to train for the remote sensing domain or perform poorly without annotation. We posit that in expert domains like r...

Rishabh Mondal, Nipun Batra, Utkarsh Mall · 0 citations
Sep 2026

A Semi-Parametric Framework For Open Vocabulary Panoptic Segmentation

Open vocabulary panoptic segmentation aims to jointly predict semantic categories and instance masks for arbitrary userspecified concepts, including categories not observed during training. Existing approaches are predominantly parametric, relying on classifier weights learned from fixed segmentation vocabularies. As a...

Nafis Sadeq, Qing-Feng Liu, M. El-Khamy · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.