pith. sign in

arxiv: 2604.05742 · v1 · submitted 2026-04-07 · 💻 cs.CV

ASSR-Net: Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion

Qiya Song , Hongzhi Zhou , Lishan Tan , Renwei Dian , Shutao Li This is my paper

Pith reviewed 2026-05-10 18:48 UTC · model grok-4.3

classification 💻 cs.CV
keywords Hyperspectral image fusionAnisotropic structureSpectral recalibrationDirectional perceptionSpatial enhancementImage reconstructionDeep neural network
0
0 comments X

The pith

ASSR-Net reconstructs high-resolution hyperspectral images with better spatial details and spectral accuracy by using directional structure awareness and low-resolution spectral priors in two stages.

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

The paper sets out to improve hyperspectral image fusion, the task of combining inputs to produce images that are sharp in space yet rich in spectral bands. Existing approaches often leave blurred anisotropic patterns or introduce spectral shifts, so the authors introduce a two-stage network that first rebuilds spatial structures by perceiving features along several directions and then corrects spectral errors by referring back to the original low-resolution data. A reader would care because many remote-sensing and material-analysis applications depend on fused images that retain both fine spatial edges and faithful spectral signatures. If the claim holds, the result is fused output that keeps more usable information than prior networks deliver on standard test sets.

Core claim

ASSR-Net adopts a two-stage fusion strategy comprising anisotropic structure-aware spatial enhancement and hierarchical prior-guided spectral calibration. In the first stage a directional perception fusion module adaptively captures structural features along multiple orientations to reconstruct anisotropic spatial patterns. In the second stage a spectral recalibration module uses the original low-resolution hyperspectral image as a spectral prior to correct deviations in the fused results.

What carries the argument

Directional perception fusion module that captures features along multiple orientations for anisotropic spatial reconstruction, paired with a spectral recalibration module that treats the input low-resolution hyperspectral image as an explicit prior for fidelity correction.

If this is right

  • Fused images preserve finer anisotropic spatial details than previous methods
  • Spectral fidelity improves because deviations are explicitly corrected against the original low-resolution input
  • The network outperforms state-of-the-art approaches across multiple benchmark datasets
  • Both spatial anisotropy and spectral distortion are addressed within a single unified architecture

Where Pith is reading between the lines

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

  • The same directional-plus-prior pattern could be tested on other multi-modal fusion problems such as panchromatic sharpening or medical image registration
  • If the recalibration step proves robust, it may reduce the need for heavy post-processing in operational remote-sensing pipelines
  • Real-world deployment would require checking whether performance holds when input pairs contain sensor noise or registration errors not present in the benchmarks

Load-bearing premise

The directional perception and spectral recalibration modules solve the stated reconstruction and distortion problems on data outside the development benchmarks without introducing new artifacts.

What would settle it

Quantitative evaluation on a fresh hyperspectral fusion dataset never seen in training or validation, where the network fails to exceed current best methods on both spatial sharpness metrics and spectral consistency measures.

Figures

Figures reproduced from arXiv: 2604.05742 by Hongzhi Zhou, Lishan Tan, Qiya Song, Renwei Dian, Shutao Li.

Figure 1
Figure 1. Figure 1: Anisotropy response map of the input image. Brighter regions [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Architecture of the proposed ASSR-Net. Stage I enhances anisotropic spatial structures from the low-resolution hyperspectral image (LR-HSI) [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Detailed architecture of the Directional Attention Enhancement [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of the two complementary attention mechanisms in the [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visual comparison on the CAVE dataset. From left to right: DHIF-Net, DSPNet, LRTN, MIMO-SST, SINet, OTIAS, SRLF, ASSR-Net (ours), and [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visual comparison on the Harvard dataset. From left to right: DHIF-Net, DSPNet, LRTN, MIMO-SST, SINet, OTIAS, SRLF, ASSR-Net (ours), and [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visual results on the Gaofen5 dataset. From left to right: DHIF-Net, DSPNet, LRTN, MIMO-SST, SINet, OTIAS, SRLF, ASSR-Net (ours), and GT. [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Visual comparison of Stage I and Stage II outputs. Top row: Spectral error maps (SAM) after Stage I; middle row: Spectral error maps after Stage II; [PITH_FULL_IMAGE:figures/full_fig_p009_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Classification results before and after fusion. (a) Classification result of LR-HSI. (b) Classification result of the predicted HR-HSI. (c) Reference. [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Spectral profiles of three points (marked in the RGB images) for three different scenes.Stage 2 consistently reduces spectral deviations compared to [PITH_FULL_IMAGE:figures/full_fig_p010_10.png] view at source ↗
read the original abstract

Hyperspectral image fusion aims to reconstruct high-spatial-resolution hyperspectral images (HR-HSI) by integrating complementary information from multi-source inputs. Despite recent progress, existing methods still face two critical challenges: (1) inadequate reconstruction of anisotropic spatial structures, resulting in blurred details and compromised spatial quality; and (2) spectral distortion during fusion, which hinders fine-grained spectral representation. To address these issues, we propose \textbf{ASSR-Net}: an Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion. ASSR-Net adopts a two-stage fusion strategy comprising anisotropic structure-aware spatial enhancement (ASSE) and hierarchical prior-guided spectral calibration (HPSC). In the first stage, a directional perception fusion module adaptively captures structural features along multiple orientations, effectively reconstructing anisotropic spatial patterns. In the second stage, a spectral recalibration module leverages the original low-resolution HSI as a spectral prior to explicitly correct spectral deviations in the fused results, thereby enhancing spectral fidelity. Extensive experiments on various benchmark datasets demonstrate that ASSR-Net consistently outperforms state-of-the-art methods, achieving superior spatial detail preservation and spectral consistency.

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

0 major / 2 minor

Summary. The manuscript proposes ASSR-Net, a two-stage neural network architecture for hyperspectral image fusion. The first stage (anisotropic structure-aware spatial enhancement, ASSE) employs a directional perception fusion module to adaptively capture and reconstruct anisotropic spatial structures from multi-source inputs. The second stage (hierarchical prior-guided spectral calibration, HPSC) uses a spectral recalibration module that incorporates the original low-resolution hyperspectral image as a prior to correct spectral deviations. Extensive experiments on benchmark datasets are reported to demonstrate consistent outperformance over state-of-the-art methods in spatial detail preservation and spectral consistency.

Significance. If the reported results hold, the work provides a targeted architectural solution to two persistent challenges in hyperspectral image fusion by explicitly modeling directional anisotropy and leveraging spectral priors. The two-stage design with modular components offers a clear technical contribution that could benefit remote-sensing and imaging applications. The use of multiple standard benchmarks and the detailed module descriptions support reproducibility and allow direct comparison with prior methods.

minor comments (2)
  1. [Abstract] Abstract: The abstract claims consistent outperformance and superior spatial/spectral quality but supplies no quantitative metrics, dataset names, or error statistics. Adding a concise statement of key results (e.g., average PSNR/SSIM gains on the primary benchmarks) would strengthen the summary without lengthening it excessively.
  2. [Experiments] Experiments section: While the manuscript states that experiments support the claims, ensure that ablation studies isolating the directional perception fusion module and the spectral recalibration module are presented with quantitative tables; this would directly address the contribution of each component to the reported gains.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive evaluation of our manuscript, the accurate summary of ASSR-Net's two-stage design, and the recommendation for minor revision. We appreciate the recognition of our contributions in explicitly modeling directional anisotropy and leveraging spectral priors.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper presents an empirical deep learning architecture (ASSR-Net with ASSE and HPSC modules) for hyperspectral image fusion, trained and evaluated on standard benchmarks. No load-bearing mathematical derivations, uniqueness theorems, or predictions are claimed that reduce to inputs by construction. Performance claims rest on experimental comparisons rather than self-referential fitting or self-citation chains. The derivation chain is self-contained as a standard network design plus empirical validation.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The central claim rests on the empirical effectiveness of two newly named modules whose internal behavior is learned from data; no closed-form derivations or external benchmarks independent of training are referenced in the abstract.

free parameters (1)
  • network weights and hyperparameters
    All convolutional filters, attention weights, and training hyperparameters are fitted to the benchmark datasets during supervised training.
axioms (2)
  • domain assumption The directional perception module reconstructs anisotropic structures better than isotropic convolutions
    Invoked in the description of the first stage without proof or external validation.
  • domain assumption The original low-resolution HSI serves as a reliable spectral prior for correcting fusion artifacts
    Invoked in the description of the second stage.

pith-pipeline@v0.9.0 · 5517 in / 1218 out tokens · 61935 ms · 2026-05-10T18:48:28.772086+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

  • IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear
    ?
    unclear

    Relation between the paper passage and the cited Recognition theorem.

    ASSR-Net adopts a two-stage fusion strategy comprising anisotropic structure-aware spatial enhancement (ASSE) and hierarchical prior-guided spectral calibration (HPSC)... directional perception fusion module... spectral recalibration module

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

45 extracted references · 45 canonical work pages

  1. [1]

    Uas-based hyperspectral environmental monitoring of acid mine drainage affected waters,

    H. Flores, S. Lorenz, R. Jackisch, L. Tusa, I. C. Contreras, R. Zim- mermann, and R. Gloaguen, “Uas-based hyperspectral environmental monitoring of acid mine drainage affected waters,”Minerals, vol. 11, no. 2, 2021

    work page 2021

  2. [2]

    Tradeoffs in the spatial and spectral resolution of airborne hyperspectral imaging systems: A crop identification case study,

    J. Jia, J. Chen, X. Zheng, Y . Wang, S. Guo, H. Sun, C. Jiang, M. Karjalainen, K. Karila, Z. Duan, T. Wang, C. Xu, J. Hyypp ¨a, and Y . Chen, “Tradeoffs in the spatial and spectral resolution of airborne hyperspectral imaging systems: A crop identification case study,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–18, 2022

    work page 2022

  3. [3]

    Three-dimensional convolutional neural network model for tree species classification using airborne hyperspectral images,

    B. Zhang, L. Zhao, and X. Zhang, “Three-dimensional convolutional neural network model for tree species classification using airborne hyperspectral images,”Remote Sensing of Environment, vol. 247, p. 111938, 2020

    work page 2020

  4. [4]

    A review on hyperspectral imagery application for lithological map- ping and mineral prospecting: Machine learning techniques and future prospects,

    S. Hajaj, A. El Harti, A. B. Pour, A. Jellouli, Z. Adiri, and M. Hashim, “A review on hyperspectral imagery application for lithological map- ping and mineral prospecting: Machine learning techniques and future prospects,”Remote Sensing Applications: Society and Environment, vol. 35, p. 101218, 2024

    work page 2024

  5. [5]

    Hyperspectral imaging for military and security applications: Combining myriad processing and sensing techniques,

    M. Shimoni, R. Haelterman, and C. Perneel, “Hyperspectral imaging for military and security applications: Combining myriad processing and sensing techniques,”IEEE Geoscience and Remote Sensing Magazine, vol. 7, no. 2, pp. 101–117, 2019

    work page 2019

  6. [6]

    Hyperspectral pansharpening: A review,

    L. Loncan, L. B. de Almeida, J. M. Bioucas-Dias, X. Briottet, J. Chanus- sot, N. Dobigeon, S. Fabre, W. Liao, G. A. Licciardi, M. Sim ˜oes, J.- Y . Tourneret, M. A. Veganzones, G. Vivone, Q. Wei, and N. Yokoya, “Hyperspectral pansharpening: A review,”IEEE Geoscience and Remote Sensing Magazine, vol. 3, no. 3, pp. 27–46, 2015

    work page 2015

  7. [7]

    Improving component substitution pansharpening through multivariate regression of ms+pan data,

    B. Aiazzi, S. Baronti, and M. Selva, “Improving component substitution pansharpening through multivariate regression of ms+pan data,”IEEE Transactions on Geoscience and Remote Sensing, vol. 45, no. 10, pp. 3230–3239, 2007

    work page 2007

  8. [8]

    Mtf- tailored multiscale fusion of high-resolution ms and pan imagery,

    B. Aiazzi, L. Alparone, S. Baronti, A. Garzelli, and M. Selva, “Mtf- tailored multiscale fusion of high-resolution ms and pan imagery,” Photogrammetric Engineering and Remote Sensing, vol. 72, pp. 591– 596, 05 2006

    work page 2006

  9. [9]

    Smoothing filter-based intensity modulation: A spectral pre- serve image fusion technique for improving spatial details,

    J. G. Liu, “Smoothing filter-based intensity modulation: A spectral pre- serve image fusion technique for improving spatial details,”International Journal of Remote Sensing, vol. 21, no. 18, pp. 3461–3472, 2000

    work page 2000

  10. [10]

    Hyperspectral super- resolution by coupled spectral unmixing,

    C. Lanaras, E. Baltsavias, and K. Schindler, “Hyperspectral super- resolution by coupled spectral unmixing,” in2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 3586–3594

    work page 2015

  11. [11]

    Isgm-fus: Internal structure-guided model for multispectral and hyperspectral image fusion,

    C. Liu, J. Qian, and F. Fang, “Isgm-fus: Internal structure-guided model for multispectral and hyperspectral image fusion,”Neurocomputing, vol. 650, p. 130777, 2025

    work page 2025

  12. [12]

    Hyperspectral image fusion via a novel generalized tensor nuclear norm regularization,

    R. Dian, Y . Liu, and S. Li, “Hyperspectral image fusion via a novel generalized tensor nuclear norm regularization,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 4, pp. 7437–7448, 2025

    work page 2025

  13. [13]

    Nonlocal coupled tensor cp decomposition for hyperspectral and multispectral image fusion,

    Y . Xu, Z. Wu, J. Chanussot, P. Comon, and Z. Wei, “Nonlocal coupled tensor cp decomposition for hyperspectral and multispectral image fusion,”IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 58, no. 1, pp. 348–362, JAN 2020

    work page 2020

  14. [14]

    Unsupervised hyperspectral and multispectral image blind fusion based on deep tucker decomposition network with spatial–spectral manifold learning,

    H. Wang, Y . Xu, Z. Wu, and Z. Wei, “Unsupervised hyperspectral and multispectral image blind fusion based on deep tucker decomposition network with spatial–spectral manifold learning,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 7, pp. 12 721– 12 735, 2025

    work page 2025

  15. [15]

    Unsupervised deep tensor network for hyperspectral–multispectral image fusion,

    J. Yang, L. Xiao, Y .-Q. Zhao, and J. C.-W. Chan, “Unsupervised deep tensor network for hyperspectral–multispectral image fusion,”IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 9, pp. 13 017–13 031, 2024

    work page 2024

  16. [16]

    Hyperspectral image super-resolution via deep spatiospectral at- tention convolutional neural networks,

    J.-F. Hu, T.-Z. Huang, L.-J. Deng, T.-X. Jiang, G. Vivone, and J. Chanus- sot, “Hyperspectral image super-resolution via deep spatiospectral at- tention convolutional neural networks,”IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 12, pp. 7251–7265, 2022

    work page 2022

  17. [17]

    Hyperspectral pansharpening using deep prior and dual attention residual network,

    Y . Zheng, J. Li, Y . Li, J. Guo, X. Wu, and J. Chanussot, “Hyperspectral pansharpening using deep prior and dual attention residual network,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, pp. 8059–8076, 2020

    work page 2020

  18. [18]

    Low-rank transformer for high- resolution hyperspectral computational imaging,

    S. L. Renwei Dian, Yuanye Liu, “Low-rank transformer for high- resolution hyperspectral computational imaging,”International Journal of Computer Vision, pp. 1–16, 2024

    work page 2024

  19. [19]

    Dual spatial–spectral pyramid network with transformer for hyperspectral image fusion,

    Y . Sun, H. Xu, Y . Ma, M. Wu, X. Mei, J. Huang, and J. Ma, “Dual spatial–spectral pyramid network with transformer for hyperspectral image fusion,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–16, 2023

    work page 2023

  20. [20]

    S 2-differential feature awareness network for hyperspectral image fusion,

    Q. Song, S. Guo, T. Yang, B. Sun, R. Dian, and S. Li, “S 2-differential feature awareness network for hyperspectral image fusion,”IEEE Trans- actions on Geoscience and Remote Sensing, 2026

    work page 2026

  21. [21]

    Mimo-sst: Multi-input multi- output spatial-spectral transformer for hyperspectral and multispectral image fusion,

    J. Fang, J. Yang, A. Khader, and L. Xiao, “Mimo-sst: Multi-input multi- output spatial-spectral transformer for hyperspectral and multispectral image fusion,”IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–20, 2024

    work page 2024

  22. [22]

    Fusionmamba: Efficient remote sensing image fusion with state space model,

    S. Peng, X. Zhu, H. Deng, L.-J. Deng, and Z. Lei, “Fusionmamba: Efficient remote sensing image fusion with state space model,”IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1–16, 2024

    work page 2024

  23. [23]

    Slrcnn: Integrating sparse and low-rank with a cnn denoiser for hyperspectral and multispec- tral image fusion,

    L. Li, H. He, N. Chen, X. Kang, and B. Wang, “Slrcnn: Integrating sparse and low-rank with a cnn denoiser for hyperspectral and multispec- tral image fusion,”International Journal of Applied Earth Observation and Geoinformation, vol. 134, p. 104227, 2024

    work page 2024

  24. [24]

    Fully-connected transformer for multi-source image fusion,

    X. Wu, Z.-H. Cao, T.-Z. Huang, L.-J. Deng, J. Chanussot, and G. Vivone, “Fully-connected transformer for multi-source image fusion,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 3, pp. 2071–2088, 2025

    work page 2071

  25. [25]

    Mcfnet: Multiscale cross-domain fusion network for hsi and lidar data joint classification,

    Q. Song, F. Mo, K. Ding, L. Xiao, R. Dian, X. Kang, and S. Li, “Mcfnet: Multiscale cross-domain fusion network for hsi and lidar data joint classification,”IEEE Transactions on Geoscience and Remote Sensing, 2025

    work page 2025

  26. [26]

    Advancing hyperspectral and multispectral image fusion: An information-aware transformer-based unfolding network,

    J. Sun, B. Chen, R. Lu, Z. Cheng, C. Qu, and X. Yuan, “Advancing hyperspectral and multispectral image fusion: An information-aware transformer-based unfolding network,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 4, pp. 7407–7421, 2025

    work page 2025

  27. [27]

    Feature pyramid fusion network for hyperspectral pansharpening,

    W. Dong, Y . Yang, J. Qu, Y . Li, Y . Yang, and X. Jia, “Feature pyramid fusion network for hyperspectral pansharpening,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 1, pp. 1555–1567, 2025

    work page 2025

  28. [28]

    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, 2025

    work page 2025

  29. [29]

    Progressive spatial information- guided deep aggregation convolutional network for hyperspectral spec- tral super-resolution,

    J. Li, S. Du, R. Song, Y . Li, and Q. Du, “Progressive spatial information- guided deep aggregation convolutional network for hyperspectral spec- tral super-resolution,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 1, pp. 1677–1691, 2025

    work page 2025

  30. [30]

    Mct-net: Multi- hierarchical cross transformer for hyperspectral and multispectral image fusion,

    X. Wang, X. Wang, R. Song, X. Zhao, and K. Zhao, “Mct-net: Multi- hierarchical cross transformer for hyperspectral and multispectral image fusion,”Knowledge-Based Systems, vol. 264, p. 110362, 2023

    work page 2023

  31. [31]

    Spatial–spectral cross mamba network for hyperspectral and multispectral image fusion,

    H. Wu, Z. Sun, J. Qi, T. Zhan, Y . Xu, and Z. Wei, “Spatial–spectral cross mamba network for hyperspectral and multispectral image fusion,” IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1– 13, 2025

    work page 2025

  32. [32]

    A principle design of registration-fusion consistency: Toward interpretable deep unregistered hyperspectral image fusion,

    J. Qu, J. Cui, W. Dong, Q. Du, X. Wu, S. Xiao, and Y . Li, “A principle design of registration-fusion consistency: Toward interpretable deep unregistered hyperspectral image fusion,”IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 5, pp. 9648–9662, 2025

    work page 2025

  33. [33]

    Assessment of the space- borne enmap hyperspectral data for alteration mineral mapping: A case study of the reko diq porphyry cuau deposit, pakistan,

    S. Asadzadeh, X. Zhou, and S. Chabrillat, “Assessment of the space- borne enmap hyperspectral data for alteration mineral mapping: A case study of the reko diq porphyry cuau deposit, pakistan,”Remote Sensing of Environment, vol. 314, p. 114389, 2024

    work page 2024

  34. [34]

    A convex optimization- based coupled nonnegative matrix factorization algorithm for hyper- spectral 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 hyper- spectral and multispectral data fusion,”IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 56, no. 3, pp. 1652–1667, MAR 2018

    work page 2018

  35. [35]

    Unsupervised hyperspectral pansharpening via low-rank diffusion model,

    X. Rui, X. Cao, L. Pang, Z. Zhu, Z. Yue, and D. Meng, “Unsupervised hyperspectral pansharpening via low-rank diffusion model,”Information Fusion, vol. 107, p. 102325, 2024

    work page 2024

  36. [36]

    How expressive are transformers in spectral domain for graphs?

    A. Bastos, A. Nadgeri, K. Singh, H. Kanezashi, T. Suzumura, and I. O. Mulang’, “How expressive are transformers in spectral domain for graphs?”Transactions on Machine Learning Research, 2022

    work page 2022

  37. [37]

    A selective re-learning mechanism for hyperspectral fusion imaging,

    Y . Liu, J. Liu, R. Dian, and S. Li, “A selective re-learning mechanism for hyperspectral fusion imaging,” in2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 7437– 7446. 12

    work page 2025

  38. [38]

    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, 2010

    work page 2010

  39. [39]

    Statistics of real-world hyperspectral images,

    A. Chakrabarti and T. Zickler, “Statistics of real-world hyperspectral images,” inCVPR 2011, 2011, pp. 193–200

    work page 2011

  40. [40]

    A universal image quality index,

    Z. Wang and A. Bovik, “A universal image quality index,”IEEE Signal Processing Letters, vol. 9, no. 3, pp. 81–84, 2002

    work page 2002

  41. [41]

    Image quality assess- ment: from error visibility to structural similarity,

    Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli, “Image quality assess- ment: from error visibility to structural similarity,”IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004

    work page 2004

  42. [42]

    Deep hyperspectral image fusion network with iterative spatio-spectral regularization,

    T. Huang, W. Dong, J. Wu, L. Li, X. Li, and G. Shi, “Deep hyperspectral image fusion network with iterative spatio-spectral regularization,”IEEE Transactions on Computational Imaging, vol. 8, pp. 201–214, 2022

    work page 2022

  43. [43]

    Spatial invertible network with mamba-convolution for hyperspectral image fusion,

    L. Xiao, S. Guo, F. Mo, Q. Song, Y . Yang, Y . Liu, X. Wei, T. Yang, and R. Dian, “Spatial invertible network with mamba-convolution for hyperspectral image fusion,”IEEE Journal of Selected Topics in Signal Processing, pp. 1–12, 2025

    work page 2025

  44. [44]

    Otias: Octree implicit adaptive sampling for multispectral and hyperspectral image fusion,

    S. Deng, J. Ma, L.-J. Deng, and P. Wei, “Otias: Octree implicit adaptive sampling for multispectral and hyperspectral image fusion,” inAAAI- 25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, T. Walsh, J. Shah, and Z. Kolter, Eds. AAAI Press, 2025, pp. 2708– 2716

    work page 2025

  45. [45]

    Hyperspectral and lidar data fusion: Outcome of the 2013 grss data fusion contest,

    C. Debes, A. Merentitis, R. Heremans, J. Hahn, N. Frangiadakis, T. van Kasteren, W. Liao, R. Bellens, A. Pi ˇzurica, S. Gautama, W. Philips, S. Prasad, Q. Du, and F. Pacifici, “Hyperspectral and lidar data fusion: Outcome of the 2013 grss data fusion contest,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 6, ...

    work page 2013