SkySense-VITA: Towards Universal In-context Segmentation of Multi-modal Remote Sensing Imagery
SkySense-VITA is introduced, a unified in-context segmentation model, which synergistically processes both optical and Synthetic Aperture Radar (SAR) imagery using VI sual, T extu A l, or fused prompts, and is proposed to de-couple multi-modal prompt fusion and prediction process.
Kang Wu, Lei Yu, Junwei Luo et al.
· 1 citation