用小条扫描+小波分解，提升高光谱图像超分辨率效果
HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-Resolution
- 采用条带扫描替代单向扫描，减少生成伪影
- 结合小波分解缓解频域特征冲突，性能达最新水平
- 在保持高效的同时显著提升图像质量，适合遥感图像处理
单幅高光谱图像超分辨率（SHSR）旨在从低分辨率高光谱图像中恢复高分辨率图像。近期，Visual Mamba 模型在性能与计算效率之间取得了出色平衡。然而，由于其一维扫描范式，模型在图像生成过程中可能引入潜在伪影。为解决此问题，我们提出 HSRMamba。在保持 Visual Mamba 计算效率的基础上，引入基于条带的扫描策略，有效降低全局单向扫描带来的伪影。此外，HSRMamba 使用小波分解，缓解高频空间特征与低频光谱特征之间的模态冲突，进一步提升超分辨率性能。大量实验表明，HSRMamba 不仅显著降低计算开销与模型规模，还优于现有方法，达到当前最优结果。
原文摘要 · Abstract (English)
Single hyperspectral image super-resolution (SHSR) aims to restore high-resolution images from low-resolution hyperspectral images. Recently, the Visual Mamba model has achieved an impressive balance between performance and computational efficiency. However, due to its 1D scanning paradigm, the model may suffer from potential artifacts during image generation. To address this issue, we propose HSRMamba. While maintaining the computational efficiency of Visual Mamba, we introduce a strip-based scanning scheme to effectively reduce artifacts from global unidirectional scanning. Additionally, HSRMamba uses wavelet decomposition to alleviate modal conflicts between high-frequency spatial features and low-frequency spectral features, further improving super-resolution performance. Extensive experiments show that HSRMamba not only excels in reducing computational load and model size but also outperforms existing methods, achieving state-of-the-art results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。