From Mechanism to Decision in 3D Point-Cloud Learning And Hyperspectral Image Learning: Cross-Scale Reasoning and Reproducibility

Abstract

Progress in 3D point-cloud learning and hyperspectral image learning depends on more than accumulating favorable results. This critical synthesis connects hierarchical spatial state-space aggregation for point-cloud classification with bidirectional nonlinear spatial-spectral feature learning for hyperspectral images and asks how measurement choices, boundary conditions, and decision costs shape the interpretation of both. A structured reading of two target studies and 12 verified companion references is conducted across five lenses: neighborhood construction, hierarchy, state-space mixing, sampling robustness, efficiency. Emphasis is placed on the provenance of evidence, the comparability of baselines, and the consequences of alternative explanations. The combined literature indicates that methodological gains become actionable only when neighborhood construction and hierarchy are evaluated together and when limits associated with efficiency are explicit. This shifts the emphasis from isolated scores toward traceable chains of evidence and decision relevance. The resulting framework supports reproducible comparison while preserving differences between study designs, and it identifies concrete points at which transfer claims should be narrowed or retested.