D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal
This addresses the problem of spatially localized degradation in images for computer vision applications, representing an incremental improvement with novel architectural components.
The paper tackled shadow removal in images by proposing a Mamba-based network with dual-scale fusion and dual-path scanning to integrate contextual cues and model region-specific transformations, achieving state-of-the-art performance on benchmarks.
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.