Dual-Camera Super-Resolution with Aligned Attention Modules
ICCV 2021 (Oral Presentation)
-
Tengfei Wang*
HKUST -
Jiaxin Xie*
HKUST -
Wenxiu Sun
SenseTime -
Qiong Yan
SenseTime -
Qifeng Chen
HKUST
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.
Architecture
Overview of our pipeline.
Results
BibTeX
@InProceedings{wang2021DCSR, author = {Wang, Tengfei and Xie, Jiaxin and Sun, Wenxiu and Yan, Qiong and Chen, Qifeng}, title = {Dual-Camera Super-Resolution with Aligned Attention Modules}, booktitle = {International Conference on Computer Vision (ICCV)}, year = {2021} }