SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xin, Zepeng, Li, Kaiyu, Chen, Luodi, Li, Wanchen, Xiao, Yuchen, Qiao, Hui, Zhang, Weizhan, Meng, Deyu, Cao, Xiangyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912785235968000
author Xin, Zepeng
Li, Kaiyu
Chen, Luodi
Li, Wanchen
Xiao, Yuchen
Qiao, Hui
Zhang, Weizhan
Meng, Deyu
Cao, Xiangyong
author_facet Xin, Zepeng
Li, Kaiyu
Chen, Luodi
Li, Wanchen
Xiao, Yuchen
Qiao, Hui
Zhang, Weizhan
Meng, Deyu
Cao, Xiangyong
contents Effectively grounding complex language to pixels in remote sensing (RS) images is a critical challenge for applications like disaster response and environmental monitoring. Current models can parse simple, single-target commands but fail when presented with complex geospatial scenarios, e.g., segmenting objects at various granularities, executing multi-target instructions, and interpreting implicit user intent. To drive progress against these failures, we present LaSeRS, the first large-scale dataset built for comprehensive training and evaluation across four critical dimensions of language-guided segmentation: hierarchical granularity, target multiplicity, reasoning requirements, and linguistic variability. By capturing these dimensions, LaSeRS moves beyond simple commands, providing a benchmark for complex geospatial reasoning. This addresses a critical gap: existing datasets oversimplify, leading to sensitivity-prone real-world models. We also propose SegEarth-R2, an MLLM architecture designed for comprehensive language-guided segmentation in RS, which directly confronts these challenges. The model's effectiveness stems from two key improvements: (1) a spatial attention supervision mechanism specifically handles the localization of small objects and their components, and (2) a flexible and efficient segmentation query mechanism that handles both single-target and multi-target scenarios. Experimental results demonstrate that our SegEarth-R2 achieves outstanding performance on LaSeRS and other benchmarks, establishing a powerful baseline for the next generation of geospatial segmentation. All data and code will be released at https://github.com/earth-insights/SegEarth-R2.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20013
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
Xin, Zepeng
Li, Kaiyu
Chen, Luodi
Li, Wanchen
Xiao, Yuchen
Qiao, Hui
Zhang, Weizhan
Meng, Deyu
Cao, Xiangyong
Computer Vision and Pattern Recognition
Effectively grounding complex language to pixels in remote sensing (RS) images is a critical challenge for applications like disaster response and environmental monitoring. Current models can parse simple, single-target commands but fail when presented with complex geospatial scenarios, e.g., segmenting objects at various granularities, executing multi-target instructions, and interpreting implicit user intent. To drive progress against these failures, we present LaSeRS, the first large-scale dataset built for comprehensive training and evaluation across four critical dimensions of language-guided segmentation: hierarchical granularity, target multiplicity, reasoning requirements, and linguistic variability. By capturing these dimensions, LaSeRS moves beyond simple commands, providing a benchmark for complex geospatial reasoning. This addresses a critical gap: existing datasets oversimplify, leading to sensitivity-prone real-world models. We also propose SegEarth-R2, an MLLM architecture designed for comprehensive language-guided segmentation in RS, which directly confronts these challenges. The model's effectiveness stems from two key improvements: (1) a spatial attention supervision mechanism specifically handles the localization of small objects and their components, and (2) a flexible and efficient segmentation query mechanism that handles both single-target and multi-target scenarios. Experimental results demonstrate that our SegEarth-R2 achieves outstanding performance on LaSeRS and other benchmarks, establishing a powerful baseline for the next generation of geospatial segmentation. All data and code will be released at https://github.com/earth-insights/SegEarth-R2.
title SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.20013