Interpretable Deep Multimodal Image Super-Resolution

Abstract

Multimodal image super-resolution (SR) is the reconstruction of a high resolution image given a low-resolution observation with the aid of another image modality. While existing deep multimodal models do not incorporate domain knowledge about image SR, we present a multimodal deep network design that integrates coupled sparse priors and allows the effective fusion of information from another modality into the reconstruction process. Our method is inspired by a novel iterative algorithm for coupled convolutional sparse coding, resulting in an interpretable network by design. We apply our model to the super-resolution of near-infrared image guided by RGB images. Experimental results show that our model outperforms state-of-the-art methods.

in Proceedings of iTWIST'20, Paper-ID: 41, Nantes, France, December, 2-4, 2020

References in corpus (3)

• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Feedback Network for Image Super-Resolution
• Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion