Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning
Yingkai Zhang, Tao Zhang, Jing Nie, Ying Fu
Abstract
Unregistered hyperspectral image (HSI) super-resolution (SR) typically aims to enhance a low-resolution HSI using an unregistered high-resolution reference image. In this paper, we propose an unmixing-based fusion framework that decouples spatial-spectral information to simultaneously mitigate the impact of unregistered fusion and enhance the learnability of SR models. Specifically, we first utilize singular value decomposition for initial spectral unmixing, preserving the original endmembers while dedicating the subsequent network to enhancing the initial abundance map. To leverage the spatial texture of the unregistered reference, we introduce a coarse-to-fine deformable aggregation module, which first estimates a pixel-level flow and a similarity map using a coarse pyramid predictor. It further performs fine sub-pixel refinement to achieve deformable aggregation of the reference features. The aggregative features are then refined via a series of spatial-channel abundance cross-attention blocks. Furthermore, a spatial-channel modulated fusion module is presented to merge encoder-decoder features using dynamic gating weights, yielding a high-quality, high-resolution HSI. Experimental results on simulated and real datasets confirm that our proposed method achieves state-of-the-art super-resolution performance. The code will be available at https://github.com/yingkai-zhang/UAFL.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Degradation-Aware Metric Prompting for Hyperspectral Image Restoration cites Real Noise Decoupling for Hyperspectral Image Denoising
- Degradation-Aware Metric Prompting for Hyperspectral Image Restoration cites ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution
Cited by top-tier papers1
Builds on10
- ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolutionMingjin Zhang, Chi Zhang, Qiming Zhang, Jie Guo et al.ICCV 2023 · 73 citations
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image ReconstructionZhiyang Yao, Shuyang Liu, Xiaoyun Yuan, Lu FangCVPR 2024 · 34 citations
- Enhancing Video Super-Resolution via Implicit Resampling-based AlignmentKai Xu, Ziwei Yu, Xin Wang, Michael Bi Mi et al.CVPR 2024 · 22 citations
- MPI-Flow: Learning Realistic Optical Flow with Multiplane ImagesYingping Liang, Jiaming Liu, Debing Zhang, Ying FuICCV 2023 · 12 citations
- Real Noise Decoupling for Hyperspectral Image DenoisingYingkai Zhang, Tao Zhang, Jing Nie, Ying FuAAAI 2026 · 3 citations
Related papers
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolutionWenqian Dong, Yang Xu, Jiahui Qu, Shaoxiong HouAAAI 2024 · 12 citations
- Unsupervised Adaptation Learning for Hyperspectral Imagery Super-ResolutionLei Zhang, Jiangtao Nie, Wei Wei, Yanning Zhang et al.CVPR 2020
- Breaking the Spatial-Temporal Consistency Constraint: Towards Reference-Based Hyperspectral Image Super-ResolutionXuyao Liu, Jiahui Qu, Wenqian DongACM MM 2025
- SCPSN: Spectral Clustering-based Pyramid Super-resolution Network for Hyperspectral ImagesYong Yang, Aoqi Zhao, Shuying Huang, Xiaozheng Wang et al.ACM MM 2024 · 5 citations
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-ResolutionXi Su, Xiangfei Shen, Mingyang Wan, Jing Nie et al.AAAI 2025 · 3 citations
