# Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling

arXiv: https://arxiv.org/abs/2605.31048 · HTML: https://mlsanity.com/paper/2605.31048/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures](https://mlsanity.com/paper/2503.01113/) (2025)
- [Fine-tuning vision foundation model for crack segmentation in civil infrastructures](https://mlsanity.com/paper/2312.04233/) (2023)
- [Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation](https://mlsanity.com/paper/2408.12815/) (2024)
- [An Efficient and Mixed Heterogeneous Model for Image Restoration](https://mlsanity.com/paper/2504.10967/) (2025)
- [Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection](https://mlsanity.com/paper/2109.05707/) (2021)
- [Vision Mamba-based autonomous crack segmentation on concrete, asphalt, and masonry surfaces](https://mlsanity.com/paper/2406.16518/) (2024)
- [Segment Any Crack: Deep Semantic Segmentation Adaptation for Crack Detection](https://mlsanity.com/paper/2504.14138/) (2025)
- [MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention](https://mlsanity.com/paper/2603.01361/) (2026)
- [An Implementation of the Crack Topology Score with Extensions](https://mlsanity.com/paper/2601.10762/) (2026)

## Built on by (most cited first, 1 of 1)

- [CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation](https://mlsanity.com/paper/2609.05816/) (2026)

## Abstract (arXiv)

Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, and auxiliary enhancement branches. Although effective, this raises whether stronger generic feature mixing is the most suitable direction for crack segmentation. We instead formulate crack segmentation as sparse structural recovery. Cracks have limited category-level semantics but strong morphological regularities, being thin, sparse, anisotropic, locally fragmented, and easily confused with textures or shadows. Thus, the key bottleneck lies in preserving weak structural evidence, recovering directional continuity, and suppressing background coupling. We propose RIFT, a compact family of morphology-aligned crack segmentation models. Rather than compressing a complex generic architecture, RIFT is simple by design, preserving local evidence, aggregating cooperative directional continuity, and restoring crack structures through lightweight multi-scale fusion. Experiments on four public benchmarks show that RIFT achieves the best or tied-best results across the 16 main metrics against reproduced representative baselines. RIFT-B gives the strongest overall accuracy, while RIFT-T provides the best deployment efficiency with only 0.47M parameters and high inference speed. Topology-aware evaluation, ablations, transfer experiments, and visualizations further verify that task-aligned simplicity can match or surpass complex hybrid architectures when its inductive bias fits crack morphology. Code: https://github.com/xauat-liushipeng/RIFT