Hyperspectral Image Generation with Unmixing Guided Diffusion Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909742501199872 |
|---|---|
| author | Shen, Shiyu Pan, Bin Zhang, Ziye Shi, Zhenwei |
| author_facet | Shen, Shiyu Pan, Bin Zhang, Ziye Shi, Zhenwei |
| contents | We address hyperspectral image (HSI) synthesis, a problem that has garnered growing interest yet remains constrained by the conditional generative paradigms that limit sample diversity. While diffusion models have emerged as a state-of-the-art solution for high-fidelity image generation, their direct extension from RGB to hyperspectral domains is challenged by the high spectral dimensionality and strict physical constraints inherent to HSIs. To overcome the challenges, we introduce a diffusion framework explicitly guided by hyperspectral unmixing. The approach integrates two collaborative components: (i) an unmixing autoencoder that projects generation from the image domain into a low-dimensional abundance manifold, thereby reducing computational burden while maintaining spectral fidelity; and (ii) an abundance diffusion process that enforces non-negativity and sum-to-one constraints, ensuring physical consistency of the synthesized data. We further propose two evaluation metrics tailored to hyperspectral characteristics. Comprehensive experiments, assessed with both conventional measures and the proposed metrics, demonstrate that our method produces HSIs with both high quality and diversity, advancing the state of the art in hyperspectral data generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02601 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hyperspectral Image Generation with Unmixing Guided Diffusion Model Shen, Shiyu Pan, Bin Zhang, Ziye Shi, Zhenwei Computer Vision and Pattern Recognition Image and Video Processing We address hyperspectral image (HSI) synthesis, a problem that has garnered growing interest yet remains constrained by the conditional generative paradigms that limit sample diversity. While diffusion models have emerged as a state-of-the-art solution for high-fidelity image generation, their direct extension from RGB to hyperspectral domains is challenged by the high spectral dimensionality and strict physical constraints inherent to HSIs. To overcome the challenges, we introduce a diffusion framework explicitly guided by hyperspectral unmixing. The approach integrates two collaborative components: (i) an unmixing autoencoder that projects generation from the image domain into a low-dimensional abundance manifold, thereby reducing computational burden while maintaining spectral fidelity; and (ii) an abundance diffusion process that enforces non-negativity and sum-to-one constraints, ensuring physical consistency of the synthesized data. We further propose two evaluation metrics tailored to hyperspectral characteristics. Comprehensive experiments, assessed with both conventional measures and the proposed metrics, demonstrate that our method produces HSIs with both high quality and diversity, advancing the state of the art in hyperspectral data generation. |
| title | Hyperspectral Image Generation with Unmixing Guided Diffusion Model |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2506.02601 |