SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom

@article{Mei2021SDANSD,
  title={SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom},
  author={Kangfu Mei and Shenglong Ye and Rui Huang},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.00848}
}
Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to the difficulty in learning misaligned optical zoom. In this paper, we introduce a Squared Deformable Alignment Network (SDAN) to address this issue. Our network learns squared per-point offsets for convolutional kernels, and then aligns features in corrected… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 22 REFERENCES
Deformable Convolutional Networks
Understanding Deformable Alignment in Video Super-Resolution
EDVR: Video Restoration With Enhanced Deformable Convolutional Networks
Image Super-Resolution Using Deep Convolutional Networks
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Enhanced Deep Residual Networks for Single Image Super-Resolution
Multi-scale Residual Network for Image Super-Resolution
Zoom to Learn, Learn to Zoom
Deformable ConvNets V2: More Deformable, Better Results
...
1
2
3
...