MDCwFB: A Multilevel Dense Connection Network with Feedback Connections for Pansharpening

Li, Weisheng; Xiang, Minghao; Liang, Xuesong

doi:10.3390/rs13112218

Cited by 4 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To adapt the input to the multi-level network structure, differential inputs at three different levels are required [31]. The differential objects must have the same size and dimension; thus, the PAN image must be processed to the same dimension as MS images in three layers [32].…”

Section: Acquisition Of Differential Informationmentioning

confidence: 99%

Differential Strategy-Based Multi-Level Dense Network for Pansharpening

Yin

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Due to the discrepancy in spatial structure between multispectral (MS) and panchromatic (PAN) images, the general fusion scheme will lead to image error in the fused result. To solve this issue, a differential strategy-based multi-level dense network is proposed, and it regards the image pairs at different scales as the input of the network at different levels and is able to map the spatial information in PAN images to each band of MS images well by learning the differential information of different levels, which effectively solves the scale effect of remote sensing images. An improved dense network with the same hierarchical structure is used to obtain richer spatial features to enhance the spatial information of the fused result. Meanwhile, a hybrid loss strategy is used to constrain the network at different levels for obtaining better results. Qualitative and quantitative analyses show that the result has a uniform spectral distribution, a complete spatial structure, and optimal evaluation criteria, which fully demonstrate the superior performance of the proposed method.

show abstract

Section: Acquisition Of Differential Informationmentioning

confidence: 99%

Differential Strategy-Based Multi-Level Dense Network for Pansharpening

Yin

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning (DL) methods have sprung up due to their super nonlinear fitting ability and abstract feature extraction ability. At present, the pansharpening network based on DL mainly includes the network based on residual connection (detail injection based CNN, DiCNN) [21], the network based on densely connection (multilevel dense connection network with feedback connections, MDCwFB) [22], based on generative adversarial network (generative adversarial network for Pan-sharpening, PSGAN) [23] and the transformer-based network (HyperTransformer) [24]. In the latest study, Zhou et al [25] introduce a novel pansharpening network using cross-modality joint learning.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Interactive Dual-Stream Network for Pansharpening

Guo,

Jia,

Yang

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Pansharpening is crucial for obtaining highresolution multispectral images. Existing deep learning-based pansharpening networks rely on supervised learning with external reference labels. Due to the lack of actual fusion results for labeling, simulated degraded data is used with the original multispectral image as the fusion result label. This process steps are cumbersome, which also leads to the problem of scale degradation, and the fusion relationship between data before and after the degradation cannot represent the real fusion relationship. To address these limitations, we propose a selfsupervised interactive dual-stream network for pansharpening (SIDP) using real training datasets. Our approach incorporates a dual-stream network architecture, comprising a spatial scale enhancement stream and a spectral channel attention stream. Spatial and spectral features essential for fusion are extracted from the original panchromatic and multispectral images, respectively. Through interconnection at different levels, the network expands the search range in the feature space, enabling continuous interaction between spatial and spectral information during feature extraction and transmission. This ensures the injection of spatial features of varying scales into correspondingscale spectral features, enhancing complementarity between features. Moreover, we introduce a novel joint spatial-spectral loss function, leveraging the original panchromatic and multispectral images themselves as self-supervised labels. Experimental results on diverse satellite datasets demonstrate the outstanding fusion performance of our method, as assessed through both subjective qualitative evaluation and objective quantitative evaluation. Furthermore, our proposed method exhibits exceptional generalization performance for full-scale remote sensing images, showcasing its practical value.

show abstract