DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models

Understand

The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge.

• Unlike object-centric natural images, RS imagery is fundamentally characterized by extreme target sparsity and massive spatial redundancy.
• Key objects of interest (e.g., ships, vehicles) often occupy less than 1% of the spatial extent, surrounded by vast, target-free backgrounds.
• Existing VFMs predominantly rely on uniform dense processing (e.g., ViTs) and pixel-reconstruction pre-training paradigms (e.g., MAE).