Preprint
Sep 2026
Radiation, Rotation and Scale Invariant Feature Descriptor for Multimodal Image Matching
A radiation, rotation, and scale invariant (RRSI) feature descriptor that enables feature encoding, interaction, and fusion across intra-modal, dual-head sampled, and inter-modal regions, and introduces a bidirectional cross-modal generative reconstruction constraint during training.
Yuan-Xin Ye, Teng-Feng Tang, Tao Peng et al.
· 0 citations