pith. sign in

arxiv: 2604.19007 · v1 · submitted 2026-04-21 · 📡 eess.IV

ExplainS2A: Explainable Spectral-Spatial Duality Model for Fast Transforming Sentinel-2 Image to AVIRIS-Level Hyperspectral Image

Chia-Hsiang Lin , Zi-Chao Leng This is my paper

Pith reviewed 2026-05-10 02:11 UTC · model grok-4.3

classification 📡 eess.IV
keywords spectral super-resolutionhyperspectral imagingSentinel-2AVIRISimage fusiondeep unfoldingexplainable modelremote sensing
0
0 comments X

The pith

Spectral super-resolution of Sentinel-2 images is reframed as spatial super-resolution via duality theory to produce AVIRIS-level hyperspectral output.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that spectral super-resolution of multispectral Sentinel-2 images into hyperspectral images can be recast as a spatial super-resolution task by using inherent high-resolution bands to guide reconstruction. This spectral-spatial duality lets the authors build ExplainS2A as a single framework that merges spectral recovery with spatial fusion through a deep unfolding network and an explainable fusion module. The resulting model runs as a linear-time algorithm, processes million-scale images in under a second, and delivers high-fidelity hyperspectral images that improve material identification. It is demonstrated on Sentinel-2 to AVIRIS conversion but positioned as a general method for other sensor pairs, with shown ability to generalize across regions and seasons.

Core claim

The central claim is that the tough spectral super-resolution problem reduces to a spatial super-resolution problem because the fusion step that uses high-resolution bands to sharpen the initial low-resolution hyperspectral estimate coincides exactly with known spatial super-resolution techniques; ExplainS2A implements this reduction through a deep unfolding network for spectral recovery followed by an explainable fusion network, yielding an interpretable linear-time procedure that converts Sentinel-2 multispectral data into high-fidelity AVIRIS-level hyperspectral images.

What carries the argument

The spectral-spatial duality theory, which reformulates spectral super-resolution as spatial super-resolution by leveraging high-resolution bands within the multispectral input to guide fusion.

If this is right

  • The model produces usable hyperspectral images from standard Sentinel-2 acquisitions in under one second per million pixels.
  • Blind source separation results improve when the generated hyperspectral images replace lower-fidelity inputs.
  • The same framework applies to other multispectral-to-hyperspectral sensor pairs that share similar resolution configurations.
  • Cross-region and cross-season generalization occurs without retraining, supporting operational deployment over diverse areas.
  • Interpretability is retained because the network is built from unfolding and explicit fusion steps rather than a black-box architecture.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the duality holds more broadly, the same reformulation could accelerate hyperspectral synthesis from other common multispectral satellite sources without new sensor development.
  • Real-time onboard processing on small satellites becomes feasible because the linear-time property scales to large scenes.
  • Downstream tasks such as mineral mapping or vegetation health monitoring could shift from requiring dedicated hyperspectral missions to using existing multispectral archives.
  • Extending the unfolding network to incorporate additional physical constraints like atmospheric correction might further reduce the need for post-processing.

Load-bearing premise

The assumption that the fusion of low-resolution hyperspectral estimates with high-resolution bands inside the multispectral image exactly matches a spatial super-resolution problem and that this duality holds without loss of spectral or spatial information for the Sentinel-2 and AVIRIS sensor pair.

What would settle it

Acquire co-located Sentinel-2 and AVIRIS imagery over the same ground scene, run ExplainS2A on the Sentinel-2 data, and directly compare the output hyperspectral cube against the real AVIRIS measurements using spectral angle and spatial edge metrics; systematic large discrepancies would falsify the duality claim.

Figures

Figures reproduced from arXiv: 2604.19007 by Chia-Hsiang Lin, Zi-Chao Leng.

Figure 1
Figure 1. Figure 1: The overview of the proposed ExplainS2A algorithm. ExplainS2A [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The proposed ExplainS2A spectral super-resolution algorithm for computationally transforming Sentinel-2 image [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: (a) The reference GT over four representative land types. The spatial [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 3
Figure 3. Figure 3: (a) The reference AVIRIS data YH over four representative land types, where 10 representative pixels (i.e., spectrally distinct pixels, marked by red dots) are selected from each land type for evaluating the spectral fidelity of the reconstructed hyperspectral pixels (cf [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Spectral reconstruction results of SSU-Net, COS2A, and the proposed [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: (a) Testing ROIs (same as Figure 6), and the SAM error maps for the [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: The scalability analysis of the proposed ExplainS2A algorithm, [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Stable performances of ExplainS2A across diverse challenging [PITH_FULL_IMAGE:figures/full_fig_p012_9.png] view at source ↗
Figure 11
Figure 11. Figure 11: (a) BSS results obtained from the Sentinel-2 data [PITH_FULL_IMAGE:figures/full_fig_p013_11.png] view at source ↗
read the original abstract

Mainstream optical satellites often acquire multispectral multi-resolution images, which have limited material identifiability compared to the HSIs. Thus, spectrally super-resolving the MSI into their hyperspectral counterparts greatly facilitates remote material identification and the downstream tasks. However, spectrally super-resolving the MSI into an HSI is often constrained by the multi-resolution nature of the sensor. Specifically, due to the presence of some LR bands in the MSI, the initial spectral super-resolution results often appear to be spatially blurry, resulting in an LR HSI. To overcome this bottleneck, we then leverage some HR band inherent in the acquired MSI to spatially guide the reconstruction procedure, thereby yielding the desired HR HSI. This fusion procedure elegantly coincides with a widely known spatial super-resolution problem in satellite remote sensing. Hence, we have reformulated the tough spectral super-resolution problem into a more widely investigated spatial super-resolution problem, referred to as the spectral-spatial duality theory. Accordingly, we propose ExplainS2A, consisting of a deep unfolding network and an explainable fusion network, that unifies spectral recovery and spatial fusion into a single explainable framework. Unlike conventional black-box models, ExplainS2A offers interpretability and operates as a linear-time algorithm. Remarkably, it can process a million-scale Sentinel-2 image in less than one second, yielding high-fidelity HSI over the same scene, and upgrades the blind source separation results. Although demonstrated on the Sentinel-2 and AVIRIS sensors, ExplainS2A also serves as a general framework applicable to various sensor pairs with different resolution configurations, and has experimentally demonstrated cross-region and cross-season generalization ability. Source codes: https://github.com/IHCLab/ExplainS2A.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper claims that the spectral super-resolution of multi-resolution Sentinel-2 MSI to AVIRIS-level HSI can be reformulated as a spatial super-resolution problem via a 'spectral-spatial duality theory': initial spectral SR produces a spatially blurry LR HSI, after which HR bands inherent in the MSI provide guidance for fusion, which 'elegantly coincides' with standard spatial SR. The proposed ExplainS2A model unifies spectral recovery (via deep unfolding) and explainable fusion into a single interpretable, linear-time framework that processes million-scale images in under one second, yields high-fidelity results, upgrades blind source separation, and generalizes across regions, seasons, and sensor pairs.

Significance. If the duality holds without information loss and the empirical results are robust, the work would offer a practical, efficient, and interpretable route to hyperspectral data from ubiquitous multispectral satellite imagery, benefiting downstream remote-sensing tasks such as material identification. Strengths include the public source code (enabling reproducibility), the explicit framing as a general framework for arbitrary sensor pairs, and the emphasis on linear-time operation and explainability over black-box alternatives.

major comments (2)
  1. [§2.2] The central duality claim (abstract; §2.2) asserts that the two-stage procedure is information-equivalent to spatial SR without loss, yet no formal equivalence proof, information-theoretic argument, or analysis of sensor-specific degradations (spectral response functions, PSFs, noise) is supplied to show that residual spectral distortion from the first stage cannot propagate. This is load-bearing for the reformulation and for the assertion that the problem is thereby 'widely investigated.'
  2. [§4] Experiments (§4) report cross-region and cross-season generalization and high-fidelity results, but lack an ablation that isolates the duality reformulation step from the deep-unfolding and fusion architecture; without it, it is impossible to determine whether performance gains derive from the claimed theory or from the network design alone.
minor comments (2)
  1. [§3] The abstract states that ExplainS2A 'operates as a linear-time algorithm,' but the complexity derivation and big-O analysis are not explicitly shown in the method section; adding this would strengthen the efficiency claim.
  2. [§4] Figure captions in the results section could more clearly label the input Sentinel-2 bands, the intermediate LR HSI, and the final output to aid visual assessment of the duality stages.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and insightful comments. We address each major comment point by point below, indicating the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [§2.2] The central duality claim (abstract; §2.2) asserts that the two-stage procedure is information-equivalent to spatial SR without loss, yet no formal equivalence proof, information-theoretic argument, or analysis of sensor-specific degradations (spectral response functions, PSFs, noise) is supplied to show that residual spectral distortion from the first stage cannot propagate. This is load-bearing for the reformulation and for the assertion that the problem is thereby 'widely investigated.'

    Authors: We appreciate the referee's emphasis on rigor for this foundational claim. The manuscript in §2.2 presents the duality as a conceptual reformulation: the initial spectral super-resolution of multi-resolution MSI yields a spatially blurry LR HSI, after which the inherent HR bands enable a fusion step that directly aligns with standard spatial SR. While this is supported by the procedural description and empirical outcomes, we acknowledge that no formal equivalence proof, information-theoretic bound, or explicit analysis of sensor degradations (e.g., SRFs, PSFs, noise propagation) is provided to rule out residual distortion carry-over. In the revised manuscript, we will add a new subsection in §2.2 that supplies a rigorous argument, including an information-theoretic perspective on equivalence under the observed degradations and a brief analysis showing that first-stage spectral residuals are mitigated by the subsequent fusion without invalidating the reformulation. revision: yes

  2. Referee: [§4] Experiments (§4) report cross-region and cross-season generalization and high-fidelity results, but lack an ablation that isolates the duality reformulation step from the deep-unfolding and fusion architecture; without it, it is impossible to determine whether performance gains derive from the claimed theory or from the network design alone.

    Authors: We agree that isolating the contribution of the duality reformulation is necessary to attribute performance gains correctly. The current experiments in §4 demonstrate overall effectiveness, cross-region/season generalization, and comparisons to baselines, but do not include an ablation that removes or bypasses the duality-based reformulation while retaining the deep-unfolding and fusion components. In the revised manuscript, we will add a targeted ablation study in §4 that compares the full ExplainS2A against a variant performing direct spectral super-resolution without the duality-guided spatial fusion step. This will clarify whether the reported gains stem from the reformulation itself or primarily from the network architecture. revision: yes

Circularity Check

0 steps flagged

No significant circularity; duality is observational reformulation

full rationale

The paper observes that MSI multi-resolution bands cause initial spectral SR to produce spatially blurry LR HSI, after which HR-band guidance reduces to standard spatial SR; this is labeled 'spectral-spatial duality theory' and used to motivate a unified deep-unfolding + explainable-fusion architecture. No equations, fitted parameters, or self-citations are shown reducing the central claim to its own inputs by construction. The reformulation is presented as a conceptual reframing of sensor characteristics rather than a self-definitional loop or renamed fitted result. The model itself is offered as an independent implementation with claimed linear-time performance and generalization, keeping the derivation chain self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim depends on the validity of the duality theory as a domain assumption and the performance of the proposed neural network architecture, with no explicit free parameters or additional invented physical entities mentioned in the abstract.

axioms (1)
  • domain assumption Spectral super-resolution of multispectral images can be reformulated as spatial super-resolution using spectral-spatial duality.
    This is the core reformulation stated in the abstract that enables the approach.
invented entities (1)
  • ExplainS2A no independent evidence
    purpose: Unifies spectral recovery and spatial fusion in an explainable, fast framework.
    Newly proposed model consisting of deep unfolding and fusion networks.

pith-pipeline@v0.9.0 · 5633 in / 1461 out tokens · 49082 ms · 2026-05-10T02:11:50.724023+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

65 extracted references · 65 canonical work pages

  1. [1]

    Identifiability of the simplex volume minimization criterion for blind hyperspectral unmixing: The no-pure-pixel case,

    C.-H. Lin, W.-K. Ma, W.-C. Li, C.-Y . Chi, and A. Ambikapathi, “Identifiability of the simplex volume minimization criterion for blind hyperspectral unmixing: The no-pure-pixel case,”IEEE Transactions on Geoscience and Remote Sensing, vol. 53, no. 10, pp. 5530–5546, May 2015

    work page 2015

  2. [2]

    Sentinel-2: ESA’s optical high-resolution mission for GMES operational services,

    M. Druschet al., “Sentinel-2: ESA’s optical high-resolution mission for GMES operational services,”Remote Sensing of Environment, vol. 120, pp. 25–36, May 2012

    work page 2012

  3. [3]

    A VIRIS Data Portal,

    “A VIRIS Data Portal,” [Online]. Available: https://aviris.jpl.nasa.gov/ dataportal/ [Accessed: Oct. 17, 2025]

    work page 2025

  4. [4]

    A full-spectrum time- reversal deep network for label imbalance learning: A case study with novel ground-truth labeling strategy for mangrove forest change detec- tion,

    C.-H. Lin, W.-H. Li, S.-M. Hsu, and H.-J. Chu, “A full-spectrum time- reversal deep network for label imbalance learning: A case study with novel ground-truth labeling strategy for mangrove forest change detec- tion,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, pp. 1–15, Sep. 2025

    work page 2025

  5. [5]

    Sentinel-2 data for land cover/use mapping: A review,

    D. Phiri, M. Simwanda, S. Salekin, V . R. Nyirenda, Y . Murayama, and M. Ranagalage, “Sentinel-2 data for land cover/use mapping: A review,” Remote Sensing, vol. 12, no. 14, pp. 1–35, Jul. 2020

    work page 2020

  6. [6]

    Remote sensing for precision agriculture: Sentinel-2 improved features and applications,

    J. Segarra, M. L. Buchaillot, J. L. Araus, and S. C. Kefauver, “Remote sensing for precision agriculture: Sentinel-2 improved features and applications,”Agronomy, vol. 10, no. 5, pp. 1–18, May 2020

    work page 2020

  7. [7]

    Spectral super-resolution via adversarial unfolding and data-driven spectrum regularization: From multispectral satellite data to NASA hyperspectral image,

    S.-S. Young and C.-H. Lin, “Spectral super-resolution via adversarial unfolding and data-driven spectrum regularization: From multispectral satellite data to NASA hyperspectral image,” inProc. IEEE Conference on Computer Vision and Pattern Recognition, Denver, Colorado, USA, 3–7 Jun. 2026

    work page 2026

  8. [8]

    Spectral super-resolution via deep low- rank tensor representation,

    R. Dian, Y . Liu, and S. Li, “Spectral super-resolution via deep low- rank tensor representation,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 3, pp. 5140–5150, Mar. 2025. 15

    work page 2025

  9. [9]

    Generalized assorted pixel camera: Postcapture control of resolution, dynamic range, and spectrum,

    F. Yasuma, T. Mitsunaga, D. Iso, and S. K. Nayar, “Generalized assorted pixel camera: Postcapture control of resolution, dynamic range, and spectrum,”IEEE Transactions on Image Processing, vol. 19, no. 9, pp. 2241–2253, Sep. 2010

    work page 2010

  10. [10]

    Spectral super-resolution meets deep learning: Achievements and challenges,

    J. He, Q. Yuan, J. Li, Y . Xiao, D. Liu, H. Shen, and L. Zhang, “Spectral super-resolution meets deep learning: Achievements and challenges,” Information Fusion, vol. 97, pp. 1–22, Sep. 2023

    work page 2023

  11. [11]

    Significant remote sensing vegetation indices: A review of developments and applications,

    J. Xue and B. Su, “Significant remote sensing vegetation indices: A review of developments and applications,”Journal of Sensors, vol. 2017, no. 1, pp. 1–17, May 2017

    work page 2017

  12. [12]

    Metasurface- empowered snapshot hyperspectral imaging with convex/deep (CODE) small-data learning theory,

    C.-H. Lin, S.-H. Huang, T.-H. Lin, and P.-C. Wu, “Metasurface- empowered snapshot hyperspectral imaging with convex/deep (CODE) small-data learning theory,”Nature Communications, vol. 14, no. 1, pp. 1–10, Nov. 2023

    work page 2023

  13. [13]

    A fea- sibility study for signal-in-space design for LEO-PNT solutions with miniaturized satellites,

    R. M. Ferre, J. Praks, G. Seco-Granados, and E. S. Lohan, “A fea- sibility study for signal-in-space design for LEO-PNT solutions with miniaturized satellites,”IEEE Journal on Miniaturization for Air and Space Systems, vol. 3, no. 4, pp. 171–183, Sep. 2022

    work page 2022

  14. [14]

    All-addition hyperspectral compressed sensing for metasurface-driven miniaturized satellite,

    C.-H. Lin and T.-H. Lin, “All-addition hyperspectral compressed sensing for metasurface-driven miniaturized satellite,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–15, Mar. 2021

    work page 2021

  15. [15]

    Advances in information processing and biological imaging using flat optics,

    X. Wanget al., “Advances in information processing and biological imaging using flat optics,”Nature Reviews Electrical Engineering, vol. 1, no. 6, pp. 391–411, May 2024

    work page 2024

  16. [16]

    HyperQUEEN: Hyperspectral quantum deep network for image restoration,

    C.-H. Lin and Y .-Y . Chen, “HyperQUEEN: Hyperspectral quantum deep network for image restoration,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–20, May 2023

    work page 2023

  17. [17]

    Quantum information- empowered graph neural network for hyperspectral change detection,

    C.-H. Lin, T.-H. Lin, and J. Chanussot, “Quantum information- empowered graph neural network for hyperspectral change detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, Nov. 2024

    work page 2024

  18. [18]

    PRIME: Unsupervised multispectral unmixing using virtual quantum prism and convex geometry,

    C.-H. Lin and J.-T. Lin, “PRIME: Unsupervised multispectral unmixing using virtual quantum prism and convex geometry,”IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1–15, Feb. 2025

    work page 2025

  19. [19]

    Underdetermined blind source separation via weighted simplex shrinkage regularization and quantum deep image prior,

    C.-H. Lin and S.-S. Young, “Underdetermined blind source separation via weighted simplex shrinkage regularization and quantum deep image prior,”IEEE Transactions on Image Processing, pp. 1–1, 2026

    work page 2026

  20. [20]

    MST++: Multi-stage spectral-wise transformer for effi- cient spectral reconstruction,

    Y . Cai, J. Lin, Z. Lin, H. Wang, Y . Zhang, H. Pfister, R. Timofte, and L. Van-Gool, “MST++: Multi-stage spectral-wise transformer for effi- cient spectral reconstruction,” inProc. IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 Jun. 2022, pp. 744–754

    work page 2022

  21. [21]

    COS2A: Conversion from Sentinel-2 to A VIRIS hyperspectral data using interpretable algo- rithm with spectral–spatial duality,

    C.-H. Lin, J.-T. Chen, Z.-C. Leng, and J.-T. Lin, “COS2A: Conversion from Sentinel-2 to A VIRIS hyperspectral data using interpretable algo- rithm with spectral–spatial duality,”IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1–16, Oct. 2025

    work page 2025

  22. [22]

    ADMM-ADAM: A new inverse imaging framework blending the advantages of convex optimization and deep learning,

    C.-H. Lin, Y .-C. Lin, and P.-W. Tang, “ADMM-ADAM: A new inverse imaging framework blending the advantages of convex optimization and deep learning,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–16, Sep. 2021

    work page 2021

  23. [23]

    CODE-MM: Convex deep mangrove mapping algorithm based on optical satellite images,

    C.-H. Lin, M.-C. Chu, and P.-W. Tang, “CODE-MM: Convex deep mangrove mapping algorithm based on optical satellite images,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–19, Sep. 2023

    work page 2023

  24. [24]

    Hyperspectral change detection using semi- supervised graph neural network and convex deep learning,

    T.-H. Lin and C.-H. Lin, “Hyperspectral change detection using semi- supervised graph neural network and convex deep learning,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–18, Jun. 2023

    work page 2023

  25. [25]

    CODE-IF: A convex/deep image fusion algorithm for efficient hyperspectral super-resolution,

    C.-H. Lin, C.-Y . Hsieh, and J.-T. Lin, “CODE-IF: A convex/deep image fusion algorithm for efficient hyperspectral super-resolution,”IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–18, Apr. 2024

    work page 2024

  26. [26]

    Fast reconstruction of hyperspectral image from its RGB counterpart using ADMM-Adam theory,

    C.-H. Lin, T.-H. Lin, T.-H. Lin, and T.-H. Lin, “Fast reconstruction of hyperspectral image from its RGB counterpart using ADMM-Adam theory,” inProc. Workshop on Hyperspectral Imaging and Signal Pro- cessing: Evolution in Remote Sensing, Rome, Italy, 13–16 Sep. 2022, pp. 1–5

    work page 2022

  27. [27]

    Chi, W.-C

    C.-Y . Chi, W.-C. Li, and C.-H. Lin,Convex Optimization for Signal Processing and Communications: From Fundamentals to Applications. Boca Raton, FL, USA: CRC Press, 2017

    work page 2017

  28. [28]

    Adam: A method for stochastic optimization,

    D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” inProc. International Conference on Learning Representations, San Diego, CA, USA, May 7-9, 2015

    work page 2015

  29. [29]

    CR-Famba: A frequency-domain assisted mamba for thin cloud removal in optical remote sensing imagery,

    J. Liu, B. Pan, and Z. Shi, “CR-Famba: A frequency-domain assisted mamba for thin cloud removal in optical remote sensing imagery,”IEEE Transactions on Multimedia, vol. 27, pp. 5659–5668, Feb. 2025

    work page 2025

  30. [30]

    A quantum- empowered SPEI drought forecasting algorithm using spatially aware mamba network,

    P.-W. Tang, C.-H. Lin, J.-K. Huang, and A. R. Huete, “A quantum- empowered SPEI drought forecasting algorithm using spatially aware mamba network,”IEEE Transactions on Geoscience and Remote Sens- ing, vol. 63, pp. 1–18, 2025

    work page 2025

  31. [31]

    Unmixing guided unsupervised network for RGB spectral super-resolution,

    Q. Qu, B. Pan, X. Xu, T. Li, and Z. Shi, “Unmixing guided unsupervised network for RGB spectral super-resolution,”IEEE Transactions on Image Processing, vol. 32, pp. 4856–4867, Aug. 2023

    work page 2023

  32. [32]

    Spectral-cascaded diffusion model for remote sensing image spectral super-resolution,

    B. Chen, L. Liu, C. Liu, Z. Zou, and Z. Shi, “Spectral-cascaded diffusion model for remote sensing image spectral super-resolution,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–14, Aug. 2024

    work page 2024

  33. [33]

    Deep unfolding network for spatiospectral image super-resolution,

    Q. Ma, J. Jiang, X. Liu, and J. Ma, “Deep unfolding network for spatiospectral image super-resolution,”IEEE Transactions on Compu- tational Imaging, vol. 8, pp. 28–40, Dec. 2021

    work page 2021

  34. [34]

    Multistage spatial-spectral fusion network for spectral super-resolution,

    Y . Wu, R. Dian, and S. Li, “Multistage spatial-spectral fusion network for spectral super-resolution,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 7, pp. 12 736–12 746, Jul. 2025

    work page 2025

  35. [35]

    RepCPSI: Coordinate- preserving proximity spectral interaction network with reparameteriza- tion for lightweight spectral super-resolution,

    C. Wu, J. Li, R. Song, Y . Li, and Q. Du, “RepCPSI: Coordinate- preserving proximity spectral interaction network with reparameteriza- tion for lightweight spectral super-resolution,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–13, Apr. 2023

    work page 2023

  36. [36]

    SSU-Net: A novel spectral–spatial dual–branch U-Net for spectral superresolution in wide-area multispectral remote sensing imagery,

    W. Zhang, M. Jin, B. Zhang, Z. Li, W. Song, and J. Pan, “SSU-Net: A novel spectral–spatial dual–branch U-Net for spectral superresolution in wide-area multispectral remote sensing imagery,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 22 656–22 672, Jul. 2025

    work page 2025

  37. [37]

    A convex optimization- based coupled nonnegative matrix factorization algorithm for hyperspec- tral and multispectral data fusion,

    C.-H. Lin, F. Ma, C.-Y . Chi, and C.-H. Hsieh, “A convex optimization- based coupled nonnegative matrix factorization algorithm for hyperspec- tral and multispectral data fusion,”IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 3, pp. 1652–1667, Nov. 2017

    work page 2017

  38. [38]

    An explicit and scene-adapted definition of convex self-similarity prior with application to unsupervised Sentinel-2 super-resolution,

    C.-H. Lin and J. M. Bioucas-Dias, “An explicit and scene-adapted definition of convex self-similarity prior with application to unsupervised Sentinel-2 super-resolution,”IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 5, pp. 3352–3365, Dec. 2019

    work page 2019

  39. [39]

    Comparison of commonly used image interpolation methods,

    D. Han, “Comparison of commonly used image interpolation methods,” inProc. International Conference on Computer Science and Electronics Engineering, Hangzhou, China, 22-23 Mar. 2013, pp. 1556–1559

    work page 2013

  40. [40]

    Sentinel-2 Google Earth Engine,

    “Sentinel-2 Google Earth Engine,” [Online]. Available: https://developers.google.com/earth-engine/datasets/catalog/ COPERNICUS S2 SR HARMONIZED [Accessed: Oct. 17, 2025]

    work page 2025

  41. [41]

    Understanding the difficulty of training deep feedforward neural networks,

    X. Glorot and Y . Bengio, “Understanding the difficulty of training deep feedforward neural networks,” inProc. International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13-15 May 2010, pp. 249–256

    work page 2010

  42. [42]

    Hyper- spectral image superresolution: An edge-preserving convex formulation,

    M. Sim ˜oes, J. Bioucas-Dias, L. B. Almeida, and J. Chanussot, “Hyper- spectral image superresolution: An edge-preserving convex formulation,” inProc. IEEE International Conference on Image Processing, Paris, France, 27-30 Oct. 2014, pp. 4166–4170

    work page 2014

  43. [43]

    QR- CODE: Quasi-residual convex deep network for fusing misaligned hy- perspectral and multispectral images,

    C.-H. Lin, C.-C. Hsu, S.-S. Young, C.-Y . Hsieh, and S.-C. Tai, “QR- CODE: Quasi-residual convex deep network for fusing misaligned hy- perspectral and multispectral images,”IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–15, Mar. 2024

    work page 2024

  44. [44]

    Deep image prior,

    D. Ulyanov, A. Vedaldi, and V . Lempitsky, “Deep image prior,” inProc. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 Jun. 2018, pp. 9446–9454

    work page 2018

  45. [45]

    Learning the parts of objects by non- negative matrix factorization,

    D. D. Lee and H. S. Seung, “Learning the parts of objects by non- negative matrix factorization,”Nature, vol. 401, no. 6755, pp. 788–791, Oct. 1999

    work page 1999

  46. [46]

    Proximal algorithms,

    N. Parikh and S. Boyd, “Proximal algorithms,”Foundations and Trends® in Optimization, vol. 1, no. 3, pp. 127–239, Jan. 2014

    work page 2014

  47. [47]

    Learning proximal operators: Using denoising networks for regularizing inverse imaging problems,

    T. Meinhardt, M. Moller, C. Hazirbas, and D. Cremers, “Learning proximal operators: Using denoising networks for regularizing inverse imaging problems,” inProc. IEEE International Conference on Com- puter Vision, Oct. 2017, pp. 1781–1790

    work page 2017

  48. [48]

    Non-Local Means Denoising,

    A. Buades, B. Coll, and J.-M. Morel, “Non-Local Means Denoising,” Image Processing On Line, vol. 1, pp. 208–212, 2011

    work page 2011

  49. [49]

    Image denoising by sparse 3-D transform-domain collaborative filtering,

    K. Dabov, A. Foi, V . Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,”IEEE Transactions on Image Processing, vol. 16, no. 8, pp. 2080–2095, 2007

    work page 2080

  50. [50]

    Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,

    K. Zhang, W. Zuo, Y . Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017

    work page 2017

  51. [51]

    Reducing the carbon footprint in machine learning with eco-friendly AI training,

    T. Aggarwalet al., “Reducing the carbon footprint in machine learning with eco-friendly AI training,” inSustainable Information Security in the Age of AI and Green Computing. Hershey, PA, USA: IGI Global Scientific Publishing, 2025, pp. 201–214. 16

    work page 2025

  52. [52]

    Dense residual transformer for image denoising,

    C. Yao, S. Jin, M. Liu, and X. Ban, “Dense residual transformer for image denoising,”Electronics, vol. 11, no. 3, p. 418, Jan. 2022

    work page 2022

  53. [53]

    Unsupervised change detection in multitemporal multispectral satellite images: A convex relaxation approach,

    W.-C. Zhenget al., “Unsupervised change detection in multitemporal multispectral satellite images: A convex relaxation approach,” inIEEE International Geoscience and Remote Sensing Symposium. IEEE, 28 Jul. – 02 Aug. 2019, pp. 1546–1549

    work page 2019

  54. [54]

    DCSN: Deep com- pressed sensing network for efficient hyperspectral data transmission of miniaturized satellite,

    C.-C. Hsu, C.-H. Lin, C.-H. Kao, and Y .-C. Lin, “DCSN: Deep com- pressed sensing network for efficient hyperspectral data transmission of miniaturized satellite,”IEEE Transactions on Geoscience and Remote Sensing, vol. 59, no. 9, pp. 7773–7789, Sep. 2021

    work page 2021

  55. [55]

    Transformer-driven inverse problem transform for fast blind hyperspectral image dehazing,

    P.-W. Tang, C.-H. Lin, and Y . Liu, “Transformer-driven inverse problem transform for fast blind hyperspectral image dehazing,”IEEE Transac- tions on Geoscience and Remote Sensing, vol. 62, pp. 1–14, Jan. 2024

    work page 2024

  56. [56]

    Sedgewick and K

    R. Sedgewick and K. Wayne,Algorithms. Boston, MA, USA: Addison- Wesley Professional, 2011

    work page 2011

  57. [57]

    Signal subspace identification for incom- plete hyperspectral image with applications to various inverse problems,

    C.-H. Lin and S.-S. Young, “Signal subspace identification for incom- plete hyperspectral image with applications to various inverse problems,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1– 16, Mar. 2024

    work page 2024

  58. [58]

    SLIC superpixels compared to state-of-the-art superpixel methods,

    R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. S ¨usstrunk, “SLIC superpixels compared to state-of-the-art superpixel methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274–2282, Nov. 2012

    work page 2012

  59. [59]

    Detection of sources in non-negative blind source separation by minimum description length criterion,

    C.-H. Lin, C.-Y . Chi, L. Chen, D. J. Miller, and Y . Wang, “Detection of sources in non-negative blind source separation by minimum description length criterion,”IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 9, pp. 4022–4037, Sep. 2018

    work page 2018

  60. [60]

    A fast hyperplane- based minimum-volume enclosing simplex algorithm for blind hyper- spectral unmixing,

    C.-H. Lin, C.-Y . Chi, Y .-H. Wang, and T.-H. Chan, “A fast hyperplane- based minimum-volume enclosing simplex algorithm for blind hyper- spectral unmixing,”IEEE Transactions on Signal Processing, vol. 64, no. 8, pp. 1946–1961, Dec. 2015

    work page 1946

  61. [61]

    Vertex component analysis: A fast algorithm to unmix hyperspectral data,

    J. Nascimento and J. Dias, “Vertex component analysis: A fast algorithm to unmix hyperspectral data,”IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 4, pp. 898–910, Apr. 2005

    work page 2005

  62. [62]

    Google Earth,

    “Google Earth,” [Online]. Available: https://earth.google.com/ [Ac- cessed: Oct. 17, 2025]

    work page 2025

  63. [63]

    Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral im- agery,

    D. Heinz and C.-I. Chang, “Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral im- agery,”IEEE Transactions on Geoscience and Remote Sensing, vol. 39, no. 3, pp. 529–545, Mar. 2001

    work page 2001

  64. [64]

    Nonnegative blind source separation for ill-conditioned mixtures via John ellipsoid,

    C.-H. Lin and J. M. Bioucas-Dias, “Nonnegative blind source separation for ill-conditioned mixtures via John ellipsoid,”IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 5, pp. 2209–2223, Jul. 2020

    work page 2020

  65. [65]

    HyperKING: Quantum-classical generative adversarial networks for hyperspectral image restoration,

    C.-H. Lin and S.-S. Young, “HyperKING: Quantum-classical generative adversarial networks for hyperspectral image restoration,”IEEE Trans- actions on Geoscience and Remote Sensing, vol. 63, pp. 1–19, Apr. 2025. Chia-Hsiang Lin(S’10-M’18-SM’24) received the B.S. degree in electrical engineering and the Ph.D. degree in communications engineering from Na- tio...

    work page 2025