Welcome to SkySense family project, a series of remote sensing (RS) foundation models for earth observation. We start exploring RS foundation models from Prompt Encoder (SkySense++ and SkySense-O), RS Encoder (SkySense and SkySense-V2), and RS Decoder (SkySenseGPT), turning satellite data into actionable insights for disaster management, environmental monitoring, and more.
A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling
A Unified Foundation Model for Multi-modal Remote Sensing
A Semantic-Enhanced Multi-Modal Remote Sensing Foundation Model for Earth Observation
A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding