# D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal

arXiv: https://arxiv.org/abs/2508.12750 · HTML: https://mlsanity.com/paper/2508.12750/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Mamba for image restoration, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Mamba for image restoration](https://mlsanity.com/ssm/mamba-for-image-restoration/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Graph R-CNN for Scene Graph Generation](https://mlsanity.com/paper/1808.00191/) (2018)
- [LocalMamba: Visual State Space Model with Windowed Selective Scan](https://mlsanity.com/paper/2403.09338/) (2024)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [Auto-Exposure Fusion for Single-Image Shadow Removal](https://mlsanity.com/paper/2103.01255/) (2021)
- [Direction-aware Spatial Context Features for Shadow Detection](https://mlsanity.com/paper/1712.04142/) (2017)
- [Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04964/) (2024)
- [CANet: A Context-Aware Network for Shadow Removal](https://mlsanity.com/paper/2108.09894/) (2021)
- [Physics-based Shadow Image Decomposition for Shadow Removal](https://mlsanity.com/paper/2012.13018/) (2020)
- [SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring](https://mlsanity.com/paper/2110.05803/) (2021)
- [Leveraging Inpainting for Single-Image Shadow Removal](https://mlsanity.com/paper/2302.05361/) (2023)
- [DVMSR: Distillated Vision Mamba for Efficient Super-Resolution](https://mlsanity.com/paper/2405.03008/) (2024)
- [Recasting Regional Lighting for Shadow Removal](https://mlsanity.com/paper/2402.00341/) (2024)
- [Vim4Path: Self-Supervised Vision Mamba for Histopathology Images](https://mlsanity.com/paper/2404.13222/) (2024)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts](https://mlsanity.com/paper/2404.08589/) (2024)
- [Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolution](https://mlsanity.com/paper/2410.10140/) (2024)
- [MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs](https://mlsanity.com/paper/2408.11758/) (2024)

## Abstract (arXiv)

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.