USP-Mamba: Unmixing-Derived Spectral and Structural Prompting for Hyperspectral Image Super-Resolution
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors tackle the problem of making clearer, high-resolution hyperspectral images that keep detailed color information. They improve a recent technique called Mamba by adding special guidance based on the materials in the image and its structure, helping the model better understand and reconstruct the image. Their method uses prompts informed by the image’s content to guide the model step-by-step, preserving both local details and overall patterns. Tests on various datasets show their approach works better than previous methods.
Hyperspectral imageSuper-resolutionMamba modelSpectral unmixingState-space modelSequence modelingStructural promptsHilbert scanSemantic dependency
Authors
Shi Chen, Jie Zhang, Yicong Zhou
Abstract
Hyperspectral image super-resolution aims to reconstruct high-resolution imagery while preserving dense spectral information. Recently, Mamba-based models have shown promising potential for this task by capturing long-range dependencies with linear computational complexity. Nevertheless, their causal sequence modeling requires two-dimensional hyperspectral features to be unfolded along predefined scanning orders, which disrupts spatial adjacency and restricts the effective propagation of contextual information. Moreover, state-space parameterization of existing models is predominantly derived from generic learned representations, without explicit alignment with the intrinsic characteristics of the hyperspectral image. To address this issue, we propose an Unmixing-derived Spectral and Structural Prompting Mamba framework, termed USP-Mamba, which adapts Mamba state evolution through composition-aware spectral priors and image-dependent structural prompts. Specifically, an unmixing-informed spectral prompt captures the global material composition of the input image and provides persistent conditioning throughout reconstruction. Injected into the Mamba sequence and progressively adapted across layers, it steers state evolution toward composition-consistent reconstruction. We introduce feature-level structural prompts comprising spatial and frequency components to provide image-dependent local guidance. The spatial prompt promotes structure-sensitive state encoding for local detail preservation, while the frequency prompt enables region-adaptive transitions between homogeneous regions and high-frequency details. Finally, complementary Hilbert and Semantic-Guided Neighboring scans preserve spatial continuity and strengthen non-local semantic dependency modeling. Extensive experiments on different datasets demonstrate that the proposed method consistently outperforms representative approaches.