Lupeng Liu

Hyperspectral image (HSI) classification demands models that can jointly capture long-range spatial relations and high-dimensional spectral structures while remaining scalable to large scenes and robust under limited supervision. Existing CNN-, Transformer-, and state-space-based approaches either suffer from restricted receptive fields, quadratic attention complexity, or directional biases that hinder dense pixel-wise prediction. To address these limitations, we propose Hi-RWKV, a hierarchical recurrent weighted key–value framework tailored for hyperspectral analysis. Hi-RWKV introduces three key innovations: (1) a spatial structure–guided bidirectional propagation mechanism that integrates global spatial context while preserving boundary fidelity via edge-aware gating; (2) a spectral identity–driven channel mixing module that incorporates learnable band embeddings and whitening transforms to enhance cross-band discriminability; and (3) a multi-stage hierarchical encoder that progressively refines spectral–spatial representations with strictly linear complexity. Together, these designs enable efficient, direction-free spectral–spatial reasoning essential for large-scale HSI interpretation. Extensive experiments on four benchmarks demonstrate that Hi-RWKV consistently achieves state-of-the-art accuracy under diverse training regimes. Ablation studies confirm that each proposed module offers complementary gains in boundary preservation, spectral discrimination, and data efficiency. By unifying scalable recurrence with hyperspectral-specific structural modeling, Hi-RWKV establishes a strong and efficient paradigm for high-resolution remote sensing. The logs and source data of this article are available at https://github.com/HSI-Lab/Hi-RWKV.

Remote sensing models in incremental learning scenarios often need to contend with both the newly emerged classes and cross-domain feature shifts, a combined challenge that we name it as Cross-Domain Incremental Learning (CDIL). Existing approaches typically address Class-Incremental Learning (CIL) or Domain-Incremental Learning (DIL) separately, failing to effectively handle recurring classes across domain shifts and leading to catastrophic forgetting or misaligned features across domains. To address this gap, we propose a novel CDIL framework that integrates a frozen pre-trained backbone with domain-specific adapter modules and domain-specific prototype construction. This architecture preserves general feature representations while capturing domain-specific nuances via lightweight adapters, and it stores class prototypes from each domain to unify knowledge of recurring classes. We further introduce multi-level supervised contrastive losses to ensure consistent class representation across domains. Extensive experiments on multiple remote sensing image classification benchmarks demonstrate that the proposed method significantly outperforms state-of-the-art CIL and DIL strategies, achieving superior accuracy and retention of old knowledge under severe domain shifts. The code will be released.

Hyperspectral image (HSI), with their rich spectral information and spatial details, have demonstrated significant potential for classification tasks in fields such as remote sensing, agriculture, and environmental monitoring. However, existing methods still exhibit limitations in feature representation, primarily manifested in insufficient contextual modeling and the inability to effectively address spectral redundancy and significant variations in spatial scales. To address these challenges, this paper proposes an enhanced MambaHSI-based framework for HSI classification, focusing on improving the representation capability of spatial-spectral features. The proposed method consists of three key innovations: (1) A hierarchical DualGroupMamba module that progressively models intra-group and inter-group spectral dependencies to enhance fine-grained spectral discrimination and global contextual awareness; (2) a lightweight Hyperspectral Channel Attention (HCA) that dynamically adjusts the importance of feature channels based on the spatial–spectral information of different bands, effectively suppressing redundant information and highlighting discriminative features. (3) a Hybrid Feature Enhancer (HFE) module that effectively represents and fuses multi-scale spatial features by extracting local texture details and perceiving the overall spatial distribution of scenes, thereby enhancing the model’s adaptability to complex spatial structures. Through a systematic evaluation on four benchmark hyperspectral datasets, the proposed method achieved an average overall classification accuracy of 95.64%, outperforming the current best method by 1.89%. The experimental results validate the superior performance of the proposed approach in enhancing the representation of spatial–spectral features. The latest logs are now available at https://github.com/Tomyaya/EFR.

Hyperspectral image classification faces significant challenges due to high-dimensional spectral redundancy and complex spatial-spectral dependencies. While existing MambaHSI models leverage state-space modeling to enhance representation learning, their unidirectional formulation fails to fully capture bidirectional spatial interactions and cross-band contextual dependencies. Moreover, the uniform projection mechanism struggles to effectively distinguish spectral variations across different wavelengths. To address these limitations, we propose MambaHSI+, a novel framework that integrates bidirectional state-space modeling with spectral trajectory learning. The proposed architecture introduces three key innovations: (1) A bidirectional context modeling module, enhanced by reverse-order modeling, enables multi-directional spatial information propagation through recursive state transitions, facilitating comprehensive local-global feature aggregation while maintaining linear computational efficiency; (2) a spectral trajectory learning paradigm that formulates spectral evolution as continuous state-space process with bidirectional propagation, effectively encoding cross-band relationships; and (3) a Mamba-enhanced channel attention mechanism that adaptively emphasizes discriminative spectral features via selective state-space transformations. Extensive experiments on four benchmark datasets demonstrate state-of-the-art performance, achieving an average accuracy improvement of 2.51% over MambaHSI. By integrating state-space systems with advanced Mamba mechanisms, MambaHSI+ establishes a new paradigm for spectral-spatial representation learning, significantly advancing classification accuracy while ensuring computational efficiency. The latest logs are now available at https://github.com/RockAilab/MambaHSI_Plus.

Rock-mass point-cloud registration is a critical yet challenging task in the fields of geology and engineering. Currently, the lack of dedicated datasets for rock-mass point-cloud registration significantly limits the development and application of advanced algorithms in this area. To address this gap, we introduce RockCloud-Align, a large-scale dataset specifically designed for rock-mass point-cloud registration. Created using high-resolution LiDAR scans, this dataset covers a wide range of geological scenarios with varying densities and includes over 14,000 meticulously curated point-cloud pairs. RockCloud-Align provides a comprehensive benchmark for evaluating registration algorithms, along with a robust evaluation protocol to standardize the assessment of these methods. Building upon this dataset, we propose a novel registration method that eliminates the dependence on feature points and random sampling consensus, ensuring high efficiency and precision across diverse scenes and densities. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches in both accuracy and computational efficiency.