Recovering fine-grained details in extremely dark images remains challenging due to severe structural information loss and noise corruption. Existing enhancement methods often fail to preserve intricate details and sharp edges, limiting their effectiveness in downstream applications like text and edge detection. To address these deficiencies, we propose an efficient dual-stage approach centered on detail recovery for dark images. In the first stage, we introduce a Residual Fourier-Guided Module (RFGM) that effectively restores global illumination in the frequency domain. RFGM captures inter-stage and inter-channel dependencies through residual connections, providing robust priors for high-fidelity frequency processing while mitigating error accumulation risks from unreliable priors. The second stage employs complementary Mamba modules specifically designed for textural structure refinement: (1) Patch Mamba operates on channel-concatenated non-downsampled patches, meticulously modeling pixel-level correlations to enhance fine-grained details without resolution loss. (2) Grad Mamba explicitly focuses on high-gradient regions, alleviating state decay in state space models and prioritizing reconstruction of sharp edges and boundaries. Extensive experiments on multiple benchmark datasets and downstream applications demonstrate that our method significantly improves detail recovery performance while maintaining efficiency. Crucially, the proposed modules are lightweight and can be seamlessly integrated into existing Fourier-based frameworks with minimal computational overhead.

Pre-trained models (PTMs), recognized for their generalization capabilities, have been extensively employed in Class Incremental Learning (CIL). However, existing PTM-based CIL methods encounter two critical limitations: 1) suboptimal extraction of discriminative prototypes for classifier construction, and 2) insufficient modeling of inter-class relationships, collectively leading to catastrophic forgetting of prior knowledge when incrementally learning new classes. To address these challenges, we propose Graph-Enhanced Multimodal Prototype Alignment (GEMPA) which synergizes PTM representations with class-specific semantic information. Our framework features two key innovations: First, an Embedding Modulation (EM) module rectifies the imbalanced value distributions (characterized by Leptokurtic distribution) in PTM-generated embeddings. Second, a GCN-based Multimodal Prototype Similarity Alignment (GPA) module establishes a Visual-Semantic Co-occurrence (VSC) space through CLIP-derived semantic embeddings. This VSC space aligns visual prototypes with their corresponding semantic counterparts to model incremental class relationships. A Weighted Hybrid Loss is designed to penalize similar prototypes while maintaining the intra-class distribution in GCN. We incorporate GEMPA with seven PTM-based CIL approaches and validate them across four benchmark datasets. The results demonstrate the improvements through semantic clarity of prototypes and forgetting mitigation. Code is available at: https://github.com/AI4MyBUPT/GEMPA

Recent years have witnessed significant advances in image deraining tasks due to the emergence of numerous effective Transformers and multi-layer perceptron (MLP) models. However, these models still rely on unidirectional information flow and fail to fully exploit the potentially useful information from multiple image scales, thus limiting the robustness of the models in complex rainy scenes. To this end, we develop an effective closed-loop bidirectional scale-recurrent network (called CBS-Net) for image deraining, which organically integrates both Transformer and MLP models to jointly explore multi-scale rain representations. Specifically, we introduce a sparse Transformer block within the intra-scale branch to adaptively capture the most useful content-aware features. Furthermore, we construct a dimensional MLP block within the inter-scale branch to dynamically modulate spatial-aware features from different scales. To ensure more accurate bidirectional estimations in our scale-recurrent network, a simple yet effective feedback propagation block is embedded to perform coarse-to-fine and fine-to-coarse information communication. Extensive experimental results show that our approach achieves state-of-the-art performance on multiple benchmark datasets, demonstrating its effectiveness and scalability.

High-precision Digital Elevation Model (DEM) is crucial in geoscience, ecology, agriculture, hydrology, and other applications. In recent years, the rise of artificial intelligence algorithms such as machine learning has provided a new way to obtain high-precision DEM. However, machine learning algorithms rely on a large amount of training data, but there is currently a lack of open, unified, large-scale, and standardized multi-source DEM elevation error prediction data sets for large areas. Based on this, this paper proposes an open-source dataset, which is a large-scale elevation error prediction dataset based on TanDEM-X and AW3D30 DEMs in California, USA (T&Amp;A-DEM-California). The dataset consists of 10 feature attributes, contains 760,000 samples, and covers an area of 423,970,000 square kilometers. T&Amp;A-DEM-California not only provides academic researchers with benchmark datasets for the validation of new algorithms for machine learning but also provides a research base for future DEM calibration.