MM-OVSeg:Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wei, Yimin, Xiao, Aoran, Chen, Hongruixuan, Xia, Junshi, Yokoya, Naoto
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915894615080960
author Wei, Yimin
Xiao, Aoran
Chen, Hongruixuan
Xia, Junshi
Yokoya, Naoto
author_facet Wei, Yimin
Xiao, Aoran
Chen, Hongruixuan
Xia, Junshi
Yokoya, Naoto
contents Open-vocabulary segmentation enables pixel-level recognition from an open set of textual categories, allowing generalization beyond fixed classes. Despite great potential in remote sensing, progress in this area remains largely limited to clear-sky optical data and struggles under cloudy or haze-contaminated conditions. We present MM-OVSeg, a multimodal Optical-SAR fusion framework for resilient open-vocabulary segmentation under adverse weather conditions. MM-OVSeg leverages the complementary strengths of the two modalities--optical imagery provides rich spectral semantics, while synthetic aperture radar (SAR) offers cloud-penetrating structural cues. To address the cross-modal domain gap and the limited dense prediction capability of current vision-language models, we propose two key designs: a cross-modal unification process for multi-sensor representation alignment, and a dual-encoder fusion module that integrates hierarchical features from multiple vision foundation models for text-aligned multimodal segmentation. Extensive experiments demonstrate that MM-OVSeg achieves superior robustness and generalization across diverse cloud conditions. The source dataset and code are available at https://github.com/Jimmyxichen/MM-OVSeg.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17528
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MM-OVSeg:Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
Wei, Yimin
Xiao, Aoran
Chen, Hongruixuan
Xia, Junshi
Yokoya, Naoto
Computer Vision and Pattern Recognition
Open-vocabulary segmentation enables pixel-level recognition from an open set of textual categories, allowing generalization beyond fixed classes. Despite great potential in remote sensing, progress in this area remains largely limited to clear-sky optical data and struggles under cloudy or haze-contaminated conditions. We present MM-OVSeg, a multimodal Optical-SAR fusion framework for resilient open-vocabulary segmentation under adverse weather conditions. MM-OVSeg leverages the complementary strengths of the two modalities--optical imagery provides rich spectral semantics, while synthetic aperture radar (SAR) offers cloud-penetrating structural cues. To address the cross-modal domain gap and the limited dense prediction capability of current vision-language models, we propose two key designs: a cross-modal unification process for multi-sensor representation alignment, and a dual-encoder fusion module that integrates hierarchical features from multiple vision foundation models for text-aligned multimodal segmentation. Extensive experiments demonstrate that MM-OVSeg achieves superior robustness and generalization across diverse cloud conditions. The source dataset and code are available at https://github.com/Jimmyxichen/MM-OVSeg.
title MM-OVSeg:Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.17528