Very Deep Super-Resolution of Remotely Sensed Images with Mean Square Error and Var-norm Estimators as Loss Functions
Abstract
In this work, very deep super-resolution (VDSR) method is presented for improving the spatial resolution of remotely sensed (RS) images for scale factor 4. The VDSR net is re-trained with Sentinel-2 images and with drone aero orthophoto images, thus becomes RS-VDSR and Aero-VDSR, respectively. A novel loss function, the Var-norm estimator, is proposed in the regression layer of the convolutional neural network during re-training and prediction. According to numerical and optical comparisons, the proposed nets RS-VDSR and Aero-VDSR can outperform VDSR during prediction with RS images. RS-VDSR outperforms VDSR up to 3.16 dB in terms of PSNR in Sentinel-2 images.
- Publication:
-
arXiv e-prints
- Pub Date:
- July 2020
- DOI:
- 10.48550/arXiv.2007.15417
- arXiv:
- arXiv:2007.15417
- Bibcode:
- 2020arXiv200715417P
- Keywords:
-
- Electrical Engineering and Systems Science - Image and Video Processing;
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- 19 pages, 8 figures