AI & ML Open Release

Introduces the first billion-scale SAR vision foundation model and a massive unified benchmark for all-weather geospatial semantic segmentation.

arXiv · March 13, 2026 · 2603.12008

Ziqi Ye, Ziyang Gong, Ning Liao, Xiaoxing Hu, Di Wang, Hongruixuan Chen, Chen Huang, Yiguo He, Yuru Jia, Xiaoxing Wang, Haipeng Wang, Xue Yang, Junchi Yan

Why it matters

Synthetic Aperture Radar (SAR) is crucial for all-weather earth observation but suffers from severe domain shifts; this billion-scale release democratizes high-performance SAR analysis and provides a new standard for cross-sensor generalization.

From the abstract

Synthetic Aperture Radar (SAR) enables global, all-weather earth observation. However, owing to diverse imaging mechanisms, domain shifts across sensors and regions severely hinder its semantic generalization. To address this, we present CrossEarth-SAR, the first billion-scale SAR vision foundation model built upon a novel physics-guided sparse mixture-of-experts (MoE) architecture incorporating physical descriptors, explicitly designed for cross-domain semantic segmentation. To facilitate large