用双尺度融合与双路径扫描提升阴影去除的细节与结构一致性
D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal
- 通过双尺度融合增强多尺度特征，减少边界伪影
- 双路径扫描结合掩码感知策略，提升结构连续性与区域建模精度
- 适合图像修复、阴影去除相关研究者参考
阴影去除旨在恢复因阴影导致局部且非均匀退化的图像。与假设全局退化的通用修复任务不同，阴影去除可利用无阴影区域的丰富信息进行引导。然而，校正阴影区域所需的变换常与光照良好区域差异显著，难以采用统一策略。因此需有效整合非局部上下文信息，并自适应建模区域特异性变换。为此，我们提出一种基于Mamba的新型网络，包含双尺度融合与双路径扫描机制，根据区域间变换相似性选择性传播上下文信息。具体而言，所提出的双尺度融合Mamba模块（DFMB）通过融合原始特征与低分辨率特征，提升多尺度特征表示，有效降低边界伪影。双路径Mamba组（DPMG）通过水平扫描捕捉全局特征，并引入掩码感知的自适应扫描策略，改善结构连续性与细粒度区域建模。实验结果表明，该方法在多个阴影去除基准上显著优于现有最优方法。
原文摘要 · Abstract (English)
Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage abundant information from non-shadow regions for guidance. However, the transformation required to correct shadowed areas often differs significantly from that of well-lit regions, making it challenging to apply uniform correction strategies. This necessitates the effective integration of non-local contextual cues and adaptive modeling of region-specific transformations. To this end, we propose a novel Mamba-based network featuring dual-scale fusion and dual-path scanning to selectively propagate contextual information based on transformation similarity across regions. Specifically, the proposed Dual-Scale Fusion Mamba Block (DFMB) enhances multi-scale feature representation by fusing original features with low-resolution features, effectively reducing boundary artifacts. The Dual-Path Mamba Group (DPMG) captures global features via horizontal scanning and incorporates a mask-aware adaptive scanning strategy, which improves structural continuity and fine-grained region modeling. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches on shadow removal benchmarks.
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。