Wenhao Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenhao Hu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Jingyi Wang
State Key Laboratory of CNS/ATM and State Key Laboratory of Environment Characteristics and Effects for Near-space, Beijing Institute of Technology, Beijing, China
4 shared publications - Kun Gao
Beijing Institute of Technology
4 shared publications - Zhijia Yang
School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China
3 shared publications Baiyang Hu
2 shared publicationsJiyuan Yang
2 shared publications- Xiaodian Zhang
School of Optics and Photonics and the Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China, Beijing Institute of Technology, Beijing, China
2 shared publications
Latest Publications
- 14 October 2026
- Published by Elsevier in Information Fusion
- Vol. 139
PDRF-Net: progressive blind registration–fusion for unregistered hyperspectral image with physics consistent spatial spectral decoupling
- 14 October 2026
- Published by Elsevier in Information Fusion
- Vol. 139
PDRF-Net: progressive blind registration–fusion for unregistered hyperspectral image with physics consistent spatial spectral decoupling
- 5 October 2026
- Published by Elsevier in Neurocomputing
- Vol. 709
An adaptive modulation network for semi-dense infrared and visible image matching
- 5 October 2026
- Published by Elsevier in Neurocomputing
- Vol. 709
An adaptive modulation network for semi-dense infrared and visible image matching
- Open Access
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
PDRF-Net: Progressive Blind Registration–Fusion for Unregistered Hyperspectral Image with Physics Consistent Spatial Spectral Decoupling
Existing hyperspectral image (HSI) fusion methods typically assume well-registered image pairs, whereas real HSI and multispectral image (MSI) observations often contain rigid offsets, non-rigid deformations, and field-of-view discrepancy. Such discrepancies cause inconsistent spatial-spectral support between aggregated HSI and local MSI, leading to severe spatial–spectral mixing during fusion. To address this issue, we propose PDRF-Net, a physics-consistent progressive blind registration–fusion framework for high-resolution hyperspectral reconstruction from unregistered image pairs. PDRF-Net progressively proceeds from observation-consistent degradation prior recovery to decoupled reconstruction and refinement. Specifically, the Prior Registration–Fusion Degradation Co-optimization Module (PRE) jointly estimates rigid/non-rigid distortions and point spread function (PSF) / spectral response function (SRF) degradations to recover physically consistent priors that more completely characterize the cross-modal degradation process and explicitly relate spatially aggregated HSI observations to MSI measurements. The Spectral-Guided Unmixing Fusion (SGHF) reuses these priors to constrain abundance reconstruction and perform degradation-consistent endmember–abundance-based decoupled fusion, thereby avoiding strict pixelwise correspondence and reducing spatial–spectral mixing distortion caused by residual misalignment. The Spatial Conditioning Refinement Module (SFHR) adaptively refines spatial consistency while balancing spectral fidelity. Extensive experiments on multiple benchmarks demonstrate that PDRF-Net achieves state-of-the-art results under diverse simulated misalignments and scales, and produces higher-quality results with higher Quality with No Reference (QNR) scores on real unregistered data. The code will be released at \url{https://github.com/Gao-Kun-Lab/
- 4 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPDRF-Net: Progressive Blind Registration–Fusion for Unregistered Hyperspectral Image with Physics Consistent Spatial Spectral Decoupling
Existing hyperspectral image (HSI) fusion methods typically assume well-registered image pairs, whereas real HSI and multispectral image (MSI) observations often contain rigid offsets, non-rigid deformations, and field-of-view discrepancy. Such discrepancies cause inconsistent spatial-spectral support between aggregated HSI and local MSI, leading to severe spatial–spectral mixing during fusion. To address this issue, we propose PDRF-Net, a physics-consistent progressive blind registration–fusion framework for high-resolution hyperspectral reconstruction from unregistered image pairs. PDRF-Net progressively proceeds from observation-consistent degradation prior recovery to decoupled reconstruction and refinement. Specifically, the Prior Registration–Fusion Degradation Co-optimization Module (PRE) jointly estimates rigid/non-rigid distortions and point spread function (PSF) / spectral response function (SRF) degradations to recover physically consistent priors that more completely characterize the cross-modal degradation process and explicitly relate spatially aggregated HSI observations to MSI measurements. The Spectral-Guided Unmixing Fusion (SGHF) reuses these priors to constrain abundance reconstruction and perform degradation-consistent endmember–abundance-based decoupled fusion, thereby avoiding strict pixelwise correspondence and reducing spatial–spectral mixing distortion caused by residual misalignment. The Spatial Conditioning Refinement Module (SFHR) adaptively refines spatial consistency while balancing spectral fidelity. Extensive experiments on multiple benchmarks demonstrate that PDRF-Net achieves state-of-the-art results under diverse simulated misalignments and scales, and produces higher-quality results with higher Quality with No Reference (QNR) scores on real unregistered data. The code will be released at \url{https://github.com/Gao-Kun-Lab/