.png){kind=icon}
返回
UnmixDiff: Unmixing-Based Diffusion Model for Hyperspectral Image Synthesis
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3425517.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The scarcity of hyperspectral images (HSIs) hinders the development of processing methods and downstream applications. HSI synthesis, which aims to generate realistic samples from the existing datasets, is undoubtedly a prospective and economical solution for the HSI data shortage problem. Inspired by the impressive performance of the diffusion model (DM) in image synthesis tasks, this article initiatively proposes an unmixing diffusion (UnmixDiff) model for high-quality HSI generation. The method starts with training an unmixing network to learn the distribution characteristic of objects (abundance). By incorporating the unmixing autoencoder into the DM, the UnmixDiff transforms the HSI generation into the abundance domain, which maintains the consistency of the generated spectral profile, reduces the computational complexity, and introduces a clear physical interpretation into the hyperspectral image synthesis tasks. After that, we construct a diffusion generation model in abundance space to generate realistic abundance maps. Instead of synthesizing original hyperspectral images, the proposed UnmixDiff synthesizes abundance maps to simulate objects' distribution rather than superficial textures. In this way, realistic HSI samples are generated by mixing the synthesized abundance with the scene end-members. With the comparative experiments, the proposed method achieves state-of-the-art performance in HSI synthesis tasks, effectively alleviating the HSI data scarcity and supporting widespread HSI applications. The code is available at https://github.com/yuyang95/UnmixingDM.
Keyword:
Image synthesis
Hyperspectral imaging
Task analysis
Training
Generative adversarial networks
Image reconstruction
Diffusion models
Diffusion model (DM)
hyperspectral DM
hyperspectral image (HSI) synthesis
hyperspectral unmixing (HU)
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
SpectralDiff: A Generative Framework for Hyperspectral Image Classification With Diffusion Models
OAAI
OAAI分享收藏Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
PREAI
分享收藏A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications生成对抗网络研究综述: 算法、理论与应用OAAI
OAAI分享收藏
分享收藏
查看更多内容