Dual-Camera Super-Resolution with Aligned Attention Modules
This work addresses high-quality image enhancement for smartphone photography, representing an incremental advance in reference-based super-resolution.
The paper tackles dual-camera super-resolution by proposing a method that generalizes patch-based feature matching with spatial alignment and includes self-supervised domain adaptation for real-world images, achieving clear improvements over state-of-the-art methods on a new dataset of 146 image pairs and a public benchmark.
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.