LTFormer: A light-weight transformer-based self-supervised matching network for heterogeneous remote sensing images

Wang Zhang, Tingting Li, Yuntian Zhang, Gensheng Pei, Xiruo Jiang, Yazhou Yao

Abstract: Highlights•Propose a data construction strategy to facilitate the matching process.•Develop a pyramid-based transformer network to generate deep feature descriptors.•Instantiate the LT Loss function grounded on Triplet Loss.