Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution
This addresses the challenge of acquiring paired training data for cross-modal super-resolution, which is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of self-supervised cross-modal super-resolution, where only low-resolution source and high-resolution guide images from different modalities are available, by proposing a mutual modulation SR model that achieves state-of-the-art performance in experiments.
Self-supervised cross-modal super-resolution (SR) can overcome the difficulty of acquiring paired training data, but is challenging because only low-resolution (LR) source and high-resolution (HR) guide images from different modalities are available. Existing methods utilize pseudo or weak supervision in LR space and thus deliver results that are blurry or not faithful to the source modality. To address this issue, we present a mutual modulation SR (MMSR) model, which tackles the task by a mutual modulation strategy, including a source-to-guide modulation and a guide-to-source modulation. In these modulations, we develop cross-domain adaptive filters to fully exploit cross-modal spatial dependency and help induce the source to emulate the resolution of the guide and induce the guide to mimic the modality characteristics of the source. Moreover, we adopt a cycle consistency constraint to train MMSR in a fully self-supervised manner. Experiments on various tasks demonstrate the state-of-the-art performance of our MMSR.