Boosting the Accuracy of Multispectral Image Pansharpening by Learning a Deep Residual Network

By Yancong Wei, Qiangqiang Yuan, Huanfeng Shen, Liangpei Zhang. IEEE Geoscience and Remote Sensing Letters, 2017

409 citations recorded by the source corpus.

In the field of multispectral (MS) and panchromatic image fusion (pansharpening), the impressive effectiveness of deep neural networks has recently been employed to overcome the drawbacks of the traditional linear models and boost the fusion accuracy. However, the existing methods are mainly based on simple and flat networks with relatively shallow architectures, which severely limits their performance. In this letter, the concept of residual learning is introduced to form a very deep convolutional neural network to make the full use of the high nonlinearity of the deep learning models. Through both quantitative and visual assessments on a large number of high-quality MS images from various sources, it is confirmed that the proposed model is superior to all the mainstream algorithms included in the comparison, and achieves the highest spatial–spectral unified accuracy.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b236322720184c558bfa2a43416aed7701526ec0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review (2022, methodology): “Later, numerous methods inspired by this pioneer work are presented, in which residual learning and dense connection are commonly used (Wei et al., 2017; Yang et al., 2017; Scarpa et al., 2018; Yuan et al., 2018; Peng et al., 2020; Fu et al., 2020; Lei et al., 2021).”
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators (2020, background): “Multiple works (Ren et al., 2015; Wei et al., 2017; Tai et al., 2017; Li et al., 2018b) also empirically demonstrate that deep residual network can achieve better performance on various tasks.”
Target-Adaptive CNN-Based Pansharpening (2017, background): “In [42], [43], instead, the assessment involves only”
Detail Injection-Based Deep Convolutional Neural Networks for Pansharpening (2021, methodology): “The DRPNN approach gets the worse NoPs and GFLOPs since it involves more ﬁlters and the convolutional kernels with a larger size, i.e., 7 × 7.”
Missing Data Reconstruction in Remote Sensing Image With a Unified Spatial–Temporal–Spectral Deep Convolutional Neural Network (2018, neutral): “image denoising [8], and pansharpening [9]–[13].”
A New Benchmark Based on Recent Advances in Multispectral Pansharpening: Revisiting Pansharpening With Classical and Emerging Pansharpening Methods (2021, background): “In particular, the use of CNNs with residual learning modules [107] will soon become a standard option for pansharpening, as testified to by many subsequent works [92]–[100].”