Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912868207689728 |
|---|---|
| author | Liang, Yu-Jie Cao, Zihan Deng, Liang-Jian Yang, Yang Zhang, Malu |
| author_facet | Liang, Yu-Jie Cao, Zihan Deng, Liang-Jian Yang, Yang Zhang, Malu |
| contents | Current deep learning models for Multispectral and Hyperspectral Image Fusion (MS/HS fusion) are typically designed for fixed spectral bands and spatial scales, which limits their transferability across diverse sensors. To address this, we propose SSA, a universal framework for MS/HS fusion with spectral-band and fusion-scale agnosticism. Specifically, we introduce Matryoshka Kernel (MK), a novel operator that enables a single model to adapt to arbitrary numbers of spectral channels. Meanwhile, we build SSA upon an Implicit Neural Representation (INR) backbone that models the HS signal as a continuous function, enabling reconstruction at arbitrary spatial resolutions. Together, these two forms of agnosticism enable a single MS/HS fusion model that generalizes effectively to unseen sensors and spatial scales. Extensive experiments demonstrate that our single model achieves state-of-the-art performance while generalizing well to unseen sensors and scales, paving the way toward future HS foundation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01681 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism Liang, Yu-Jie Cao, Zihan Deng, Liang-Jian Yang, Yang Zhang, Malu Image and Video Processing Computer Vision and Pattern Recognition Multimedia Current deep learning models for Multispectral and Hyperspectral Image Fusion (MS/HS fusion) are typically designed for fixed spectral bands and spatial scales, which limits their transferability across diverse sensors. To address this, we propose SSA, a universal framework for MS/HS fusion with spectral-band and fusion-scale agnosticism. Specifically, we introduce Matryoshka Kernel (MK), a novel operator that enables a single model to adapt to arbitrary numbers of spectral channels. Meanwhile, we build SSA upon an Implicit Neural Representation (INR) backbone that models the HS signal as a continuous function, enabling reconstruction at arbitrary spatial resolutions. Together, these two forms of agnosticism enable a single MS/HS fusion model that generalizes effectively to unseen sensors and spatial scales. Extensive experiments demonstrate that our single model achieves state-of-the-art performance while generalizing well to unseen sensors and scales, paving the way toward future HS foundation models. |
| title | Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2602.01681 |