高光谱遥感在多种深度学习范式中取得了进展，包括谱空 CNN、Vision Transformers、Mamba、图神经网络、Kolmogorov-Arnold 网络以及自监督掩码自动编码。然而，碎片化的代码仓库、不兼容的张量约定和非标准化的评估阻碍了进一步发展。Hyperspectral Image Models 通过一个模块化框架解决了这些挑战，该框架统一了六种范式下的 55 个代表性模型，具备通用注册表、自动 4D/5D 张量适配和标准化构造函数。它集成了来自机载、星载、无人机和火星 CRISM 传感器的 24 个基准场景，支持缓存、标签重映射、PCA、显式波段选择或原始光谱、可选空间最大池化以及任意 PxP 补丁提取。为防止重叠窗口导致准确率虚高，它支持类别平衡随机划分和带有 Chebyshev 保护带的空间不相交区域分块，从而消除训练与测试像素的重叠。实验使用单一配置、确定性种子和完整溯源信息，生成 LaTeX 基准表格和分类地图。在 1,320 次模型-场景评估和 6,600 次带种子的运行中，场景难度主导架构性能，平均准确率从 Botswana 的 96.40% 到 Houston 2018 的 56.70% 不等，而各范式均值之间的差异仅为 15 个百分点。没有一种范式具有普遍优势，且参数量低于 1M 的模型可以匹敌大两个数量级的架构。代码公开可用，地址为 https://github.com/Tanishq251/Hyperspectral-Image-Models。

Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and self supervised masked autoencoding. Yet progress remains hindered by fragmented repositories, incompatible tensor conventions, and non standardized evaluation. Hyperspectral Image Models addresses these challenges through a modular framework unifying 55 representative models across six paradigms with a common registry, automatic 4D/5D tensor adaptation, and standardized constructors. It integrates 24 benchmark scenes from Airborne, Spaceborne, UAV, and Mars CRISM sensors, with caching, label remapping, PCA, explicit band selection or raw spectra, optional spatial max pooling, and arbitrary PxP patch extraction. To prevent inflated accuracy from overlapping windows, it supports class balanced random partitioning and spatially disjoint regional blocking with Chebyshev guard bands that eliminate train test pixel overlap. Experiments use a single config with deterministic seeds and complete provenance, generating LaTeX benchmark tables and classification maps. Across 1,320 model scene evaluations and 6,600 seeded runs, scene difficulty dominates architecture, with mean accuracy ranging from 96.40% on Botswana to 56.70% on Houston 2018, versus a 15 point spread across paradigm means. No paradigm universally dominates, while sub 1 M parameter models can match architectures two orders of magnitude larger. Code is publicly available at https://github.com/Tanishq251/Hyperspectral-Image-Models.