A spectral implicit function-based method for hyperspectral remote sensing image spectral super-resolution reconstruction

doi:10.13474/j.cnki.11-2246.2026.1006

Abstract

Abstract: [Purposes] Hyperspectral remote sensing imagery is often limited by high acquisition costs and low signal-to-noise ratios.To address these challenges，this paper introduces a Transformer-based spectral implicit function (TSIF) to reconstruct high-quality hyperspectral data from low-spectral-resolution images in a low-cost manner. [Methods] The method models the wavelength-reflectance relationship of each pixel as a continuous function，employs a Transformer-based encoder to fully extract joint spatial-spectral features，and integrates target wavelength information during decoding to achieve fine-grained hyperspectral reconstruction.Additionally，the spectral angle mapper (SAM) term is incorporated into the loss function to enhance the physical consistency of the reconstructed spectra. [Findings] Experiments on two benchmark datasets demonstrate that TSIF achieves superior performance over existing methods，with an improvement of approximately 1 dB in MPSNR and a reduction of more than 0.1 in SAM，confirming its effectiveness in preserving spectral details and recovering spatial structures. [Conclusions] TSIF thus provides an efficient solution for low-cost acquisition of high-quality hyperspectral imagery．

Key words: hyperspectral remote sensing imagery, spectral implicit function, spectral super-resolution

CLC Number:

P237

Nong Xueying, Li Jiayi, Lin Xuemei, Huang Xin. A spectral implicit function-based method for hyperspectral remote sensing image spectral super-resolution reconstruction[J]. Bulletin of Surveying and Mapping, 2026, 0(10): 42-46,54.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://tb.chinasmp.com/EN/10.13474/j.cnki.11-2246.2026.1006

http://tb.chinasmp.com/EN/Y2026/V0/I10/42

References

[1] Dian Renwei，Liu Yuanye，Li Shutao.Spectral super-resolution via deep low-rank tensor representation[J].IEEE Transactions on Neural Networks and Learning Systems，2025，36(3)：5140-5150.
[2] Chen Bowen，Liu Liqin，Liu Chenyang，et al.Spectral-cascaded diffusion model for remote sensing image spectral super-resolution[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5528414.
[3] Dian Renwei，Shan Tianci，He Wei，et al.Spectral super-resolution via model-guided cross-fusion network[J].IEEE Transactions on Neural Networks and Learning Systems，2024，35(7)：10059-10070.
[4] He Jiang，Yuan Qiangqiang，Li Jie，et al.Spectral super-resolution meets deep learning：achievements and challenges[J].Information Fusion，2023，97：101812.
[5] Arad B，Ben-Shahar O.Sparse recovery of hyperspectral signal from natural RGB images[C]//Proceedings of 2016 Computer Vision-ECCV.Cham：Springer International Publishing，2016：19-34.
[6] Jia Yan，Zheng Yinqiang，Gu Lin，et al.From RGB to spectrum for natural scenes via manifold-based mapping[C]//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV).Venice：IEEE，2017：4715-4723.
[7] Wu Yaohang，Dian Renwei，Li Shutao.Multistage spatial-spectral fusion network for spectral super-resolution[J].IEEE Transactions on Neural Networks and Learning Systems，2025，36(7)：12736-12746.
[8] Shi Zhan，Chen Chang，Xiong Zhiwei，et al.HSCNN+：advanced CNN-based hyperspectral recovery from RGB images[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Salt Lake City：IEEE，2018：1052-10528.
[9] Koundinya S，Sharma H，Sharma M，et al.2D-3D CNN based architectures for spectral reconstruction from RGB images[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Salt Lake City：IEEE，2018：957-9577.
[10] Peng Hao，Chen Xiaomei，Zhao Jie.Residual pixel attention network for spectral reconstruction from RGB images[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Seattle：IEEE，2020：2012-2020.
[11] Hang Renlong，Liu Qingshan，Li Zhu.Spectral super-resolution network guided by intrinsic properties of hyperspectral imagery[J].IEEE Transactions on Image Processing，2021，30：7256-7265.
[12] Mai Gengchen，Lao Ni，Sun Weiwei，et al.SSIF：learning continuous image representation for spatial-spectral super-resolution[EB/OL].(2023-09-30)[2023-09-30].https://doi.org/10.48550/arXiv.2310.00413．
[13] Cai Yuanhao，Lin Jing，Lin Zudi，et al.MST++：multi-stage spectral-wise transformer for efficient spectral reconstruction[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).New Orleans：IEEE，2022：744-754.
[14] Mei Shaohui，Jiang Ruituo，Li Xu，et al.Spatial and spectral joint super-resolution using convolutional neural network[J].IEEE Transactions on Geoscience and Remote Sensing，2020，58(7)：4590-4603.
[15] Li Jiaojiao，Wu Chaoxiong，Song Rui，et al.Adaptive weighted attention network with camera spectral sensitivity prior for spectral reconstruction from RGB images[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Seattle：IEEE，2020：1894-1903.
[16] Zhang Lei，Lang Zhiqiang，Wang Peng，et al.Pixel-aware deep function-mixture network for spectral super-resolution[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20).Washington，DC：AAAI Press，2020：12801-12808.