13 papers
State Space Models Meet Remote Sensing: A Survey
Qinzhe Yang, Chenyang Liu, Jia Xu +2
State Space Models (SSMs), designed for long-range modeling, offer linear computational complexity and strong capabilities in capturing long-range dependencies. In the field of rem…
MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling
Zhiping Yu, Chenyang Liu, Jinqi Cao +4
Multi-modal remote sensing images are vital for Earth observation, yet complete paired observations are often scarce in practice. Existing generative methods commonly address this…
HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
Man Wang, Chenyang Liu, Wenjun Li +5
Remote sensing image change captioning (RSICC) aims to achieve high-level semantic understanding of genuine changes occurring between bi-temporal images. Despite notable progress,…
MetaEarth3D: Unlocking World-scale 3D Generation with Spatially Scalable Generative Modeling
Jinqi Cao, Zhiping Yu, Baihong Lin +3
Recent generative AI models have achieved remarkable breakthroughs in language and visual understanding. However, although these models can generate realistic visual content, their…
DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models
Keyan Chen, Chenyang Liu, Bowen Chen +4
The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge. Unlike object-…
TaCo: Capturing Spatio-Temporal Semantic Consistency in Remote Sensing Change Detection
Han Guo, Chenyang Liu, Haotian Zhang +3
Remote sensing change detection (RSCD) aims to identify surface changes across bi-temporal satellite images. Most previous methods rely solely on mask supervision, which effectivel…