Geometry Enhanced Reference-Based Image Super-Resolution

CVPRW 2023 pp. 6124-6133

doi:10.1109/CVPRW59228.2023.00652 /cvprw/2023/zou2023cvprw-geometry/

Abstract

With the prevalence of smartphones equipped with a multi-camera system comprising multiple cameras with different field-of-view (FoVs), images captured by two or three cameras now share a portion of the FoV that are compatible with reference-based super-resolution (RefSR). In this work, we propose a novel RefSR model that utilizes geometric matching methods to enhance its performance in two aspects. First, we integrate geometric matching maps to improve feature fusion. Second, we train the matching modules equipped in the RefSR models under the supervision of accurate geometric matching maps to increase their robustness. Our experimental results demonstrate the effectiveness and state-of-the-art performance of the proposed method.

CVPRW Semantic Scholar

Cite

Text

Zou et al. "Geometry Enhanced Reference-Based Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00652

Markdown

[Zou et al. "Geometry Enhanced Reference-Based Image Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/zou2023cvprw-geometry/) doi:10.1109/CVPRW59228.2023.00652

BibTeX

@inproceedings{zou2023cvprw-geometry,
  title     = {{Geometry Enhanced Reference-Based Image Super-Resolution}},
  author    = {Zou, Han and Xu, Liang and Okatani, Takayuki},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {6124-6133},
  doi       = {10.1109/CVPRW59228.2023.00652},
  url       = {https://mlanthology.org/cvprw/2023/zou2023cvprw-geometry/}
}