Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network

Abstract

In the field of fusing multi-spectral and panchromatic images (Pan-sharpening), the impressive effectiveness of deep neural networks has been recently employed to overcome the drawbacks of traditional linear models and boost the fusing accuracy. However, to the best of our knowledge, existing research works are mainly based on simple and flat networks with relatively shallow architecture, which severely limited their performances. In this paper, the concept of residual learning has been introduced to form a very deep convolutional neural network to make a full use of the high non-linearity of deep learning models. By both quantitative and visual assessments on a large number of high quality multi-spectral images from various sources, it has been supported that our proposed model is superior to all mainstream algorithms included in the comparison, and achieved the highest spatial-spectral unified accuracy.

arXiv comment5 pages,5 figures, 1 table

References in corpus (4)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Understanding Neural Networks Through Deep Visualization
• Multispectral and Hyperspectral Image Fusion Using a 3-D-Convolutional Neural Network

Cited by in corpus (28)

• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• Missing Data Reconstruction in Remote Sensing image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network
• Target-adaptive CNN-based pansharpening
• Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network
• Rethinking CNN-Based Pansharpening: Guided Colorization of Panchromatic Images via GANs
• Pansharpening by convolutional neural networks in the full resolution framework
• Spatial-Spectral Fusion by Combining Deep Learning and Variation Model
• Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening
• Deep Learning for Image Super-resolution: A Survey
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• Full-resolution quality assessment for pansharpening
• DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
• An Integrated Framework for the Heterogeneous Spatio-Spectral-Temporal Fusion of Remote Sensing Images
• Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
• Guided Deep Decoder: Unsupervised Image Pair Fusion
• Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
• PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
• PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening
• Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors
• Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
• Deep Convolutional Sparse Coding Network for Pansharpening with Guidance of Side Information
• Multispectral Pan-sharpening via Dual-Channel Convolutional Network with Convolutional LSTM Based Hierarchical Spatial-Spectral Feature Fusion
• FusionRF: High-Fidelity Satellite Neural Radiance Fields from Multispectral and Panchromatic Acquisitions
• FGF-GAN: A Lightweight Generative Adversarial Network for Pansharpening via Fast Guided Filter
• MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening
• Deep Learning-Based Detail Map Estimation for MultiSpectral Image Fusion in Remote Sensing
• Learning deep multiresolution representations for pansharpening
• Deep Gradient Projection Networks for Pan-sharpening