Dual-Camera Super-Resolution with Aligned Attention Modules

Abstract

We present a novel approach to reference-based superresolution (RefSR) with the focus on dual-camera superresolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. We further explore the dualcamera super-resolution that is one promising application of RefSR, and build a dataset that consists of 146 image pairs from the main and telephoto cameras in a smartphone. To bridge the domain gaps between realworld images and the training images, we propose a selfsupervised domain adaptation strategy for real-world images. Extensive experiments on our dataset and a public benchmark demonstrate clear improvement achieved by our method over state of the art in both quantitative evaluation and visual comparisons. Our code and data are available at https://tengfei-wang.github.io/ Dual-Camera-SR/index.html.

Fusion-based infrared single-pixel imaging

“…For infrared fusion networks, the concept of the residual block has been applied to image fusion tasks 14,15,16 . The structure of the fusion module is shown in the figure:…”