Cover Image

CrackSegFlow: Controllable Flow Matching Synthesis for Generalizable Crack Segmentation with a 50K Image-Mask Benchmark

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Asadi, Babak, Wu, Peiyang, Golparvar-Fard, Mani, Hajj, Ramez
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FMS$^2$: Unified Flow Matching for Segmentation and Synthesis of Thin Structures
by: Asadi, Babak, et al.
Published: (2026)

CrackSegDiff: Diffusion Probability Model-based Multi-modal Crack Segmentation
by: Jiang, Xiaoyan, et al.
Published: (2024)

MedFlowSeg: Flow Matching for Medical Image Segmentation with Frequency-Aware Attention
by: Chen, Zhi, et al.
Published: (2026)

Segment Any Crack: Deep Semantic Segmentation Adaptation for Crack Detection
by: Rostami, Ghodsiyeh, et al.
Published: (2025)

DSCformer: A Dual-Branch Network Integrating Enhanced Dynamic Snake Convolution and SegFormer for Crack Segmentation
by: Yu, Kaiwei, et al.
Published: (2024)

Modeling Multi-Granularity Context Information Flow for Pavement Crack Detection
by: Pang, Junbiao, et al.
Published: (2024)

Restora-Flow: Mask-Guided Image Restoration with Flow Matching
by: Hadzic, Arnela, et al.
Published: (2025)

EfficientCrackNet: A Lightweight Model for Crack Segmentation
by: Zim, Abid Hasan, et al.
Published: (2024)

CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation
by: Sadallah, Nassim, et al.
Published: (2026)

CrackUDA: Incremental Unsupervised Domain Adaptation for Improved Crack Segmentation in Civil Structures
by: Srivastava, Kushagra, et al.
Published: (2024)

Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
by: Wang, Zanyi, et al.
Published: (2025)

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
by: Li, Danfeng, et al.
Published: (2025)

CrackESS: A Self-Prompting Crack Segmentation System for Edge Devices
by: Wang, Yingchu, et al.
Published: (2024)

Context-CrackNet: A Context-Aware Framework for Precise Segmentation of Tiny Cracks in Pavement images
by: Kyem, Blessing Agyei, et al.
Published: (2025)

FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
by: Zhang, Zekang, et al.
Published: (2026)

LlamaSeg: Image Segmentation via Autoregressive Mask Generation
by: Deng, Jiru, et al.
Published: (2025)

Topology-aware Mamba for Crack Segmentation in Structures
by: Zuo, Xin, et al.
Published: (2024)

Distribution-aware Noisy-label Crack Segmentation
by: Jiang, Xiaoyan, et al.
Published: (2024)

FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching
by: Sargsyan, Andranik, et al.
Published: (2026)

FlexiCrackNet: A Flexible Pipeline for Enhanced Crack Segmentation with General Features Transfered from SAM
by: Wan, Xinlong, et al.
Published: (2025)

FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching
by: Sari, Alp Eren, et al.
Published: (2025)

Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets
by: Zhang, Xinan, et al.
Published: (2025)

FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms
by: Bogensperger, Lea, et al.
Published: (2024)

Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
by: Chen, Yifan, et al.
Published: (2026)

CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections
by: Yao, Zhen, et al.
Published: (2024)

MatchSeg: Towards Better Segmentation via Reference Image Matching
by: Huo, Jiayu, et al.
Published: (2024)

Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
by: Kompanets, Andrii, et al.
Published: (2024)

HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
by: Chen, Zerui, et al.
Published: (2026)

Benchmarking YOLOv8 for Optimal Crack Detection in Civil Infrastructure
by: Taffese, Woubishet Zewdu, et al.
Published: (2025)

FMVP: Masked Flow Matching for Adversarial Video Purification
by: Tang, Duoxun, et al.
Published: (2026)

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
by: Wang, Chaoyang, et al.
Published: (2024)

CNN-based Labelled Crack Detection for Image Annotation
by: Ilani, Mohsen Asghari, et al.
Published: (2024)

SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketches
by: Koley, Subhadeep, et al.
Published: (2025)

SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures
by: Liu, Hui, et al.
Published: (2025)

Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling
by: Liu, Shipeng, et al.
Published: (2026)

SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
by: Ye, Hanrong, et al.
Published: (2023)

Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation
by: Yang, Jie, et al.
Published: (2026)

Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation
by: Li, Fanding, et al.
Published: (2025)

TumorGen: Boundary-Aware Tumor-Mask Synthesis with Rectified Flow Matching
by: Liu, Shengyuan, et al.
Published: (2025)

Benefiting from Quantum? A Comparative Study of Q-Seg, Quantum-Inspired Techniques, and U-Net for Crack Segmentation
by: Srinivasan, Akshaya, et al.
Published: (2024)