arXiv Open Access 2020

Super-Resolving Commercial Satellite Imagery Using Realistic Training Data

Xiang Zhu Hossein Talebi Xinwei Shi Feng Yang Peyman Milanfar
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (5)

X

Xiang Zhu

H

Hossein Talebi

X

Xinwei Shi

F

Feng Yang

P

Peyman Milanfar

Format Sitasi

Zhu, X., Talebi, H., Shi, X., Yang, F., Milanfar, P. (2020). Super-Resolving Commercial Satellite Imagery Using Realistic Training Data. https://arxiv.org/abs/2002.11248

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2020
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓