CrackSSM：通过动态扫描让状态空间模型重焕生机用于裂缝分割
CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic Scanning
把 SSM 的静态多向扫描换成由高层语义方向响应驱动的动态词元重排，使裂缝相关区域在序列中相邻，这一思路可直接迁移到其他细长/不规则结构（血管、道路、裂纹）的分割与序列化建模；小波高频引导的解码也可作为边缘细化模块复用。
原文依据 we compute directional response strength along four orientations from high-level semantic features, and use these values to reorder tokens
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论裂缝分割（CS）对生产场景中的结构检测与维护至关重要。为同时实现高精度与高效率，近期方法采用了基于状态空间模型（SSM）的 Mamba 架构，其能够以线性复杂度对长程依赖建模。然而，现有方法通常依赖静态的多方向扫描将视觉特征展平为序列。这种固定的展平顺序破坏了空间连续性，并削弱了 SSM 对不规则裂缝模式的有效建模能力。为解决这一局限，我们提出 CrackSSM，一种新颖的裂缝感知分割框架，其核心是能够根据每幅图像的底层结构自适应调整词元序列的动态扫描策略。具体而言，我们从高层语义特征中计算四个方向上的方向响应强度，并利用这些值对词元重新排序，使与裂缝相关的区域在序列中保持相邻。这种对齐提升了 SSM 的因果建模能力，同时保持其效率，并更好地契合裂缝不规则、细粒度的特性。此外，我们设计了一种小波引导的解码机制以恢复细节特征。该机制引入从输入图像中提取的高频分量，并用其引导特征细化与边缘感知融合，进一步提升分割精度。在三个基准数据集上的实验表明，与现有最优模型相比，我们的方法以更少的参数和更快的推理实现了更优的分割精度。本工作源代码见 https://github.com/hby123123/CrackSSM。
英文原文摘要 1693 字符
Crack segmentation (CS) is crucial for structural inspection and maintenance in production scenarios. To achieve both high accuracy and efficiency, recent methods have adopted Mamba-based architectures built upon state space models (SSMs), which enable linear-complexity modeling of long-range dependencies. However, existing approaches typically rely on static multi-directional scanning to flatten visual features into sequences. This fixed flattening order disrupts spatial continuity and weakens the SSM's ability to model irregular crack patterns effectively. To address this limitation, we propose CrackSSM, a novel crack-aware segmentation framework featuring a dynamic scanning strategy that adapts the token sequence to the underlying structure of each image. Specifically, we compute directional response strength along four orientations from high-level semantic features, and use these values to reorder tokens so that crack-relevant regions remain adjacent in sequence. This alignment improves the causal modeling ability of SSMs while preserving their efficiency and better suits the irregular, fine-grained nature of cracks. Additionally, we design a wavelet-guided decoding mechanism to recover detailed features. It incorporates high-frequency components extracted from the input image and applies them to guide feature refinement and edge-aware fusion, further enhancing segmentation precision. Experiments on three benchmark datasets demonstrate that our method achieves superior segmentation accuracy with fewer parameters and faster inference compared to existing state-of-the-art models. The source code for this work is available at https://github.com/hby123123/CrackSSM.