Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network
arXiv:1803.04271 · doi:10.1016/j.isprsjprs.2018.09.018
Abstract
The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40->20 m, respectively 360->60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD. The code is available at https://github.com/lanha/DSen2
19 pages, 11 figures
References in corpus (2)
Cited by in corpus (27)
- Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural Networks
- Super-resolution of multispectral satellite images using convolutional neural networks
- A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-resolution
- MuS2: A Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution
- Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images
- A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery
- Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
- Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
- S3: A Spectral-Spatial Structure Loss for Pan-Sharpening Networks
- Performance of GAN-based augmentation for deep learning COVID-19 image classification
- A full-resolution training framework for Sentinel-2 image fusion
- Hybrid Inexact BCD for Coupled Structured Matrix Factorization in Hyperspectral Super-Resolution
- An Approach to Super-Resolution of Sentinel-2 Images Based on Generative Adversarial Networks
- Graph Neural Networks Extract High-Resolution Cultivated Land Maps from Sentinel-2 Image Series
- Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring
- Integrated monitoring of ice in selected Swiss lakes. Final project report
- Predicting Landsat Reflectance with Deep Generative Fusion
- Super-Resolving Beyond Satellite Hardware Using Realistically Degraded Images
- Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow
- DiffFuSR: Super-Resolution of all Sentinel-2 Multispectral Bands using Diffusion Models
- SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
- Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors
- Spatial Resolution Enhancement of Remote Sensing Mine Images using Deep Learning Techniques
- Understanding the Role of Adversarial Regularization in Supervised Learning
- Super-Resolution Appearance Transfer for 4D Human Performances
- Strict Enforcement of Conservation Laws and Invertibility in CNN-Based Super Resolution for Scientific Datasets
- Pan-Sharpening with Color-Aware Perceptual Loss and Guided Re-Colorization