Dual-Camera Super-Resolution with Aligned Attention Modules
TL
TL;DR
This work proposes a self-supervised domain adaptation strategy for real-world images that generalizes the standard patch-based feature matching with spatial alignment operations and further explores the dual-camera super-resolution that is one promising application of RefSR.
Abstract
We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (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 dual-camera 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 real-world images and the training images, we propose a self-supervised 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.
References47 items
1
Generative Adversarial Networks
2
Image Inpainting with External-internal Learning and Monochromic Bottleneck
3
Understanding Deformable Alignment in Video Super-Resolution
4
Feature Representation Matters: End-to-End Learning for Reference-Based Image Super-Resolution
5