AI RESEARCH
DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models
arXiv CS.CV
•
ArXi:2503.16426v2 Announce Type: replace 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.