MambaLIC: State-Space Models for Efficient Remote Sensing Image Compression
Remote Sensing · 12.03.2026 · 18 (6) · 881
DOI: 10.3390/rs18060881 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 12.03.2026. Verfasst von Haobo Xiong und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Remote sensing (RS) images, characterized by their large size and rich texture, require algorithms capable of effectively integrating both global and local features for compression. However, existing Learned Image Compression (LIC) approaches face distinct bottlenecks. While Transformer-based architectures typically suffer from heavy computational loads, standard State Space Models (SSMs) often incur prohibitive memory costs when processing high-resolution inputs. To address these limitations, we propose MambaLIC, a novel RS image compression network that integrates the efficient long-range modeling of SSMs with the local modeling ability of CNNs. In this paper, we introduce an innovative Remote Sensing State Space Model (RS-SSM) module, which combines visual SSM with dynamic convolution for remote sensing image compression. This integration facilitates effective interaction between local and global information, thereby enhancing the performance of RS image compression. Furthermore, we propose an SSM attention-based (SSA-based) spatial-channel context model for better entropy modeling. Compared to Transformer-CNN mixed architectures, MambaLIC reduces computational complexity by 63.9% and achieves superior rate-distortion (RD) performance. Consequently, compared to the latest SS2D-based method MambaIC, MambaLIC achieves substantial efficiency gains, saving 78.8% in memory usage. Experimental results demonstrate that MambaLIC achieves state-of-the-art (SOTA) performance, outperforming VVC (VTM-17.0) by 14.22%, 18.48%, and 17.47% in BD-rate on UC-Merced, LoveDA, and xView datasets, respectively.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
Zitieren
APA
Xiong, H., Liu, K., Xiao, H., Ding, C., & Wang, F. (2026). MambaLIC: State-Space Models for Efficient Remote Sensing Image Compression. Remote Sensing, 18(6), 881. https://doi.org/10.3390/rs18060881
Vancouver
Xiong H, Liu K, Xiao H, Ding C, Wang F. MambaLIC: State-Space Models for Efficient Remote Sensing Image Compression. Remote Sensing. 2026;18(6):881. doi:10.3390/rs18060881
BibTeX
@article{Xiong2026,
author = {Xiong, Haobo and Liu, Kai and Xiao, Huachao and Ding, Chongyang and Wang, Feiyang},
title = {MambaLIC: State-Space Models for Efficient Remote Sensing Image Compression},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {6},
pages = {881},
doi = {10.3390/rs18060881}
}
EUVIMED