SpanConv: A New Convolution via Spanning Kernel Space for Lightweight Pansharpening

Ding, Yuanyuan; Deng, Wenjin; Zheng, Yinglin; Liu, Pengfei; Wang, Meihong; Chen, Xuan; Bao, Jianmin; Chen, Dong; Zhang, Ming

doi:10.24963/ijcai.2022/118

Cited by 13 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional methods included GSA (Aiazzi, Baronti, and Selva 2007), FUSE (Wei, Dobigeon, and Tourneret 2015) and CNMF (Yokoya, Yairi, and Iwasaki 2011). The Deep Learningbased methods include PSRT (Deng et al 2023), LightNet (Chen et al 2022), LAGC-NET (Jin et al 2022), MoG-DCN (Dong et al 2021) and SSR-NET (Zhang et al 2021). Four widely used indexes are used for quantitative evaluation, including peak signal-to noise ratio (PSNR), spectral angle mapper (SAM), root mean squared error (RMSE), and erreur relative global adimensionnelle de synthese (ERGAS).…”

Section: Competing Methods and Evaluation Metricsmentioning

confidence: 99%

S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution

Qu,

He,

Dong

et al. 2024

AAAI

View full text Add to dashboard Cite

Hyperspectral image super-resolution (HISR) is a technique that can break through the limitation of imaging mechanism to obtain the hyperspectral image (HSI) with high spatial resolution. Although some progress has been achieved by existing methods, most of them directly learn the spatial-spectral joint mapping between the observed images and the target high-resolution HSI (HrHSI), failing to fully reserve the spectral distribution of low-resolution HSI (LrHSI) and the spatial distribution of high-resolution multispectral imagery (HrMSI). To this end, we propose a spatial-spectral-bilateral cycle-diffusion framework (S2CycleDiff) for HISR, which can step-wise generate the HrHSI with high spatial-spectral fidelity by learning the conditional distribution of spatial and spectral super-resolution processes bilaterally. Specifically, a customized conditional cycle-diffusion framework is designed as the backbone to achieve the spatial-spectral-bilateral super-resolution by repeated refinement, wherein the spatial/spectral guided pyramid denoising (SGPD) module seperately takes HrMSI and LrHSI as the guiding factors to achieve the spatial details injection and spectral correction. The outputs of the conditional cycle-diffusion framework are fed into a complementary fusion block to integrate the spatial and spectral details to generate the desired HrHSI. Experiments have been conducted on three widely used datasets to demonstrate the superiority of the proposed method over state-of-the-art HISR methods. The code is available at https://github.com/Jiahuiqu/S2CycleDiff.

show abstract

Section: Competing Methods and Evaluation Metricsmentioning

confidence: 99%

S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution

Qu,

He,

Dong

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Xu et al devised a modeldriven fusion network influenced by the variational optimization problem, GPPNN, which achieves excellent fusion results while maintaining a certain range of parameters [40]. In addition, Chen et al devised a lightweight network by exploring the kernel space [41].…”

Section: B Deep Learning-based Methodsmentioning

confidence: 99%

“…PRACS [30] and BDSD-PC [60]. Additionally, we select three MRA-based methods, namely AWLP [41], MTF-GLP-FS [61] and MTF-GLP-HPM-R. Furthermore, we choose eight deep learning methods, including PNN [38], PanNet [39], BDPN [62], GPPNN [40], SpanConv [41], TANI [46], TRRNet [47] and AWFLN [48].…”

Section: Comparative Methodsmentioning

confidence: 99%

Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion

Liu,

Wei,

Zhang

et al. 2023

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

View full text Add to dashboard Cite

In the field of remote sensing, image fusion technology plays a crucial role in observing the state of global resources and environmental conditions, proposing response strategies, and constantly monitoring and correcting strategies. Currently, the majority of traditional methods exhibit varying degrees of spatial or spectral distortion, and these unreasonable spectral distributions may contain erroneous geographical feature information. Meanwhile, despite their performance in fusion results, deep learning-based methods cannot be applied to some practical application scenarios due to the requirement for hardware specifications resulting from the large number of parameters in their models. These issues are not conducive to accurately reflecting the actual geomorphic resource conditions or promoting sustainable development. In order to address the above issues, we propose a novel recursive self-attention module (RSAM), which consists of two stages: spatial-spectral similarity extraction and self-attention weight generation. The proposed RSAM employs a G2L strategy to capture the global interdependencies of two distinct local locations in the feature map. This method allows for simultaneous consideration of both spatial and spectral information, while focusing on more mutual information between spectral and spatial dimensions. Subsequently, we construct the corresponding residual block (RSARB) through RSAM and concatenate the RSARBs to generate RSANet with a limited number of parameters. Extensive experiments demonstrate that RSANet achieves superior results in both qualitative and quantitative evaluation, despite the model parameters being within a narrow range of orders of magnitude. This demonstrates that the proposed method possesses robust feature learning capability and practicality for observing and studying the global resource environment. The source code will be publicly available at https://github.com/JUSTM0VE0N/RSANet.

show abstract

Pan-sharpening via conditional invertible neural network

Wang,

Lu,

Huang

et al. 2024

Information Fusion

View full text Add to dashboard Cite

SpanConv: A New Convolution via Spanning Kernel Space for Lightweight Pansharpening

Cited by 13 publications

References 2 publications

S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution

S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution

Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion

Pan-sharpening via conditional invertible neural network

Contact Info

Product

Resources

About