Jia-Bao Wang

RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Images

RoES, a Rotational Equivariant Selective-frequency fusion network, introduces a trainable rotation-enhanced updater/predictor module to dynamically decouple low- and high-frequency components, establishing a robust solution for multimodal fusion by reconciling frequency-selective features with equivariant constraints.