Super-Resolving Commercial Satellite Imagery Using Realistic Training Data
Super-Resolving Commercial Satellite Imagery Using Realistic Training Data
Xiang Zhu; Hossein Talebi; Xinwei Shi; Feng Yang; Peyman Milanfar
ICIP 2020
https://ieeexplore.ieee.org/document/9190746
https://arxiv.org/abs/2002.11248
Abstract:
In machine learning based single image super-resolution, the degradation model is embedded in training data generation. However, most existing satellite image super-resolution methods use a simple down-sampling model with a fixed kernel to create training images. These methods work fine on synthetic data, but do not perform well on real satellite images. We propose a realistic training data generation model for commercial satellite imagery products, which includes not only the imaging process on satellites but also the post-process on the ground. We also propose a convolutional neural network optimized for satellite images. Experiments show that the proposed training data generation model is able to improve super-resolution performance on real satellite images.
Видео Super-Resolving Commercial Satellite Imagery Using Realistic Training Data канала Peyman Milanfar
Xiang Zhu; Hossein Talebi; Xinwei Shi; Feng Yang; Peyman Milanfar
ICIP 2020
https://ieeexplore.ieee.org/document/9190746
https://arxiv.org/abs/2002.11248
Abstract:
In machine learning based single image super-resolution, the degradation model is embedded in training data generation. However, most existing satellite image super-resolution methods use a simple down-sampling model with a fixed kernel to create training images. These methods work fine on synthetic data, but do not perform well on real satellite images. We propose a realistic training data generation model for commercial satellite imagery products, which includes not only the imaging process on satellites but also the post-process on the ground. We also propose a convolutional neural network optimized for satellite images. Experiments show that the proposed training data generation model is able to improve super-resolution performance on real satellite images.
Видео Super-Resolving Commercial Satellite Imagery Using Realistic Training Data канала Peyman Milanfar
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Lec 4: Neyman-Pearson, ROC curve, Bayes Decision Part 1](https://i.ytimg.com/vi/g8bK9zXULJs/default.jpg)
![Lec 14: Generalized Likelihood Ratio Testing](https://i.ytimg.com/vi/YWv_NShC8Ks/default.jpg)
![Lec 5: Likelihood Ratio & Properties, Bayes Decision Part 2](https://i.ytimg.com/vi/WHcNMN3boTA/default.jpg)
![Rank-smoothed Pairwise Learning In Perceptual Quality Assessment](https://i.ytimg.com/vi/ufuMj-EiO2c/default.jpg)
![Lec 6: Matched Filters and Generalizations](https://i.ytimg.com/vi/ilF0FJhV6lI/default.jpg)
![Lec 16: Sequential Estimation, Optimal Filters, Intro to Non-parametric Estimation](https://i.ytimg.com/vi/Gi-gSoZt-D4/default.jpg)
![Projected Distribution Loss for Image Enhancement](https://i.ytimg.com/vi/UJGGa0AoqDk/default.jpg)
![Lec 8: Estimation Part 2: Cramer-Rao Bound, Stein's Unbiased Risk Estimator](https://i.ytimg.com/vi/xTh3TzdAfOs/default.jpg)
![Inversion by Direct Iteration (InDI)](https://i.ytimg.com/vi/XgRp8_B7Byw/default.jpg)
![Part 1 of "How the Mobile Phone Became a Camera", by Milanfar @ICME Keynote](https://i.ytimg.com/vi/sgNdyW0RUN8/default.jpg)
![NIMA: Neural Image Assessment](https://i.ytimg.com/vi/xMD3RXUCWtg/default.jpg)
![Lec 2: Math and Stats Background Review (Guest)](https://i.ytimg.com/vi/pm_j_cvXu80/default.jpg)
![Part 2 of "How the Mobile Phone Became a Camera", by Milanfar @ICME Keynote](https://i.ytimg.com/vi/7F1KIlOIOMM/default.jpg)
![Cnet Interview on Super Res 2001](https://i.ytimg.com/vi/yTtDLizI9vQ/default.jpg)
![Lec 18: Non-parametric Estimation Part 2](https://i.ytimg.com/vi/6BD2vre87N8/default.jpg)
![Asilomar Conference Plenary 2023](https://i.ytimg.com/vi/XYAJowhm6pE/default.jpg)
![Milanfar Keynote Full](https://i.ytimg.com/vi/ti72j2vpUcI/default.jpg)
![Lec 1: Introduction and Course Overview](https://i.ytimg.com/vi/MV1gMTg2CgM/default.jpg)
![Lec 3: Random Processes, Linear Systems. Hypothesis Testing Part 1](https://i.ytimg.com/vi/J5eh-2gdCsc/default.jpg)
![Lec 10: Midterm Review and Practice Exam](https://i.ytimg.com/vi/hr1vdMEfI5Q/default.jpg)