双门Mamba多尺度自适应特征学习网络用于无监督的单个RGB图像高光谱图像重建
Zhongmin Jiang1, Zhen Wang1, Wenju Wang1
1College of Publishing, University of Shanghai for Science and Technology, Shanghai 200093, China.
Journal of imaging
|January 27, 2026
概括
本研究引入了一种新的网络模型,用于从RGB图像中重建超光谱图像,显著提高精度和细节保存. 双门马巴多尺度自适应特征 (DMMAF) 网络实现了最先进的无监督重建性能.
科学领域:
- 计算机视觉 计算机视觉
- 图像处理 图像处理
- 机器学习 机器学习
背景情况:
- 从RGB图像中重建高光谱图像 (HSI) 具有挑战性,因为标记数据有限.
- 现有的方法遭受细节损失,不良稳定性和难以平衡空间光谱分辨率的困难.
研究的目的:
- 开发一个先进的网络模型,用于准确和强大的无监督超光谱图像重建.
- 为了解决当前方法的局限性,详细保存和空间光谱权衡.
主要方法:
- 提出了双门马巴多尺度自适应特征 (DMMAF) 学习网络.
- 引入了可适应的双噪声感应特征提取,以获得边缘细节和强度.
- 实现了全球特征的可变形注意力和本地特征的Mamba,以增强信息交互.
- 开发了一个结构意识的平滑损失函数,以平衡空间光谱分辨率.
主要成果:
- 在NTIRE 2020,哈佛和CAVE数据集上实现了最先进的无监督重建性能.
- 与现有的先进算法相比,证明了优异的结果.
- 取得的具体绩效指标:NTIRE 2020 (MRAE 0.133,RMSE 0.040,PSNR 31.314),哈佛大学 (RMSE 0.025,PSNR 34.955),CAVE (RMSE 0.041,PSNR 30.983) 取得的具体绩效指标:NTIRE 2020 (MRAE 0.133,RMSE 0.040,PSNR 31.314),哈佛大学 (RMSE 0.025,PSNR 34.955),CAVE (RMSE 0.041,PSNR 30.983) 取得的具体绩效指标:NTIRE 2020 (MRAE 0.133,RMSE 0.040,PSNR 31.314),哈佛大学 (RMSE 0.025,PSNR 34.955) 取得的具体绩效指标:NTIRE 2020 (RMSE 0.041,PSNR 30.983) 获得的具体绩效指标:
结论:
- DMMAF网络有效地克服了无监督的高光谱图像重建方面的局限性.
- 提出的方法显著提高了重建的准确性,稳定性和空间光谱平衡.
- 该模型显示了对需要高保真度高光谱成像的现实应用的巨大潜力.
更多相关视频
相关概念视频
Special Features of Adaptive Immunity
3.2K
The adaptive immune system, a crucial component of the overall immune response, offers a highly specialized defense against pathogens. It involves specific cell types and features, enabling it to combat infections effectively and efficiently.
The primary cell types involved in adaptive immunity are T cells and B cells. Each type has a unique role in defending the body against pathogens. T cells are responsible for cell-mediated immunity. They identify and eliminate infected cells directly,...
The primary cell types involved in adaptive immunity are T cells and B cells. Each type has a unique role in defending the body against pathogens. T cells are responsible for cell-mediated immunity. They identify and eliminate infected cells directly,...
3.2K
Electron Microscope Tomography and Single-particle Reconstruction
2.9K
Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...
2.9K
Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
pH Scale
79.4K
Hydronium and hydroxide ions are present both in pure water and in all aqueous solutions, and their concentrations are inversely proportional as determined by the ion product of water (Kw). The concentrations of these ions in a solution are often critical determinants of the solution’s properties and the chemical behaviors of its other solutes. Two different solutions can differ in their hydronium or hydroxide ion concentrations by a million, billion, or even trillion times. A common means of...
79.4K
Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
Ligand-Gated Ion Channel Receptor: Gating Mechanism
3.9K
Ligand-gated ion channels are transmembrane proteins that play a vital role in intercellular communication and functions of the nervous system. They allow the influx of ions across the membrane once the neurotransmitter binds, allowing the subsequent transmission of electrical excitation across the neurons. Other ligand-gated ion channels, like the γ-aminobutyric acid (GABA) receptor, permit anions like chloride into the cells on the binding of the GABA molecule. Their entry into the cell...
3.9K


