SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation

2026-05-14

AI Summary

This work addresses the challenge of balancing topological modeling accuracy and computational efficiency in pixel-level structural crack segmentation by proposing a lightweight SCRWKV network. The core innovations include a Structure-Field Encoder backbone that enables high-fidelity topological representation with linear computational complexity, and a Structure-Calibrated Insight Unit that integrates geometry-guided bidirectional structural transformation with a dynamic self-calibrated decay mechanism to effectively suppress noise and enhance structural awareness. Additionally, the model incorporates adaptive multi-scale cascaded modulation and cross-scale harmonic fusion strategies. With only 1.22 million parameters, the proposed method achieves state-of-the-art performance on the TUT dataset, yielding an F1 score of 0.8428 and an mIoU of 0.8512, significantly outperforming existing approaches.

Abstract

Achieving pixel-level accurate segmentation of structural cracks across diverse scenarios remains a formidable challenge. Existing methods face significant bottlenecks in balancing crack topology modeling with computational efficiency, often failing to reconcile high segmentation quality with low resource demands. To address these limitations, we propose the Ultra-Compact Structure-Calibrated Vision RWKV (SCRWKV), a network that achieves high-precision modeling via a novel Structure-Field Encoder (SFE) backbone while maintaining linear complexity. The SFE integrates the Adaptive Multi-scale Cascaded Modulator (AMCM) to enhance texture representation and utilizes the Structure-Calibrated Insight Unit (SCIU) as its core engine. Specifically, the SCIU employs the Geometry-guided Bidirectional Structure Transformation (GBST) to capture topological correlations and integrates the Dynamic Self-Calibrating Decay (DSCD) into Dy-WKV to suppress noise propagation. Furthermore, we introduce a lightweight Cross-Scale Harmonic Fusion (CSHF) decoder to achieve precise feature aggregation. Systematic evaluations on multiple benchmarks characterized by complex textures and severe interference demonstrate that SCRWKV, with only 1.22M parameters, significantly outperforms SOTA methods. Achieving an F1 score of 0.8428 and mIoU of 0.8512 on the TUT dataset, the model confirms its robust potential for efficient real-world deployment. The code is available at https://github.com/zhxhzy/SCRWKV.

Problem

• crack segmentation
• topological modeling
• computational efficiency
• pixel-level accuracy
• structural cracks

Innovation

• Structure-Calibrated Vision RWKV
• Topology-aware Crack Segmentation
• Linear-complexity Modeling
• Dynamic Self-Calibrating Decay
• Cross-Scale Feature Fusion