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

• URL: http://arxiv.org/abs/2601.03637v3
• Date: Sun, 11 Jan 2026 17:32:40 GMT
• Title: CrackSegFlow: Controllable Flow Matching Synthesis for Generalizable Crack Segmentation with a 50K Image-Mask Benchmark
• Abstract summary: CrackSegFlow is a controllable synthesis method that renders synthetic images of cracks from masks with pixel-level alignment.<n>Our results demonstrate that adding synthesized pairs improves in-domain performance by +5.37 mIoU and +5.13 F1, while target-guided cross-domain synthesis driven by target mask statistics adds +13.12 mIoU and +14.82 F1.
• Score: 0.27998963147546135
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments. We introduce CrackSegFlow, a controllable Flow Matching synthesis method that renders synthetic images of cracks from masks with pixel-level alignment. Our renderer combines topology-preserving mask injection with edge gating to maintain thin-structure continuity. Class-conditional FM samples masks for topology diversity, and CrackSegFlow renders aligned ground truth images from them. We further inject cracks onto crack-free backgrounds to diversify confounders and reduce false positives. Across five datasets and using a CNN-Transformer backbone, our results demonstrate that adding synthesized pairs improves in-domain performance by +5.37 mIoU and +5.13 F1, while target-guided cross-domain synthesis driven by target mask statistics adds +13.12 mIoU and +14.82 F1. We also release CSF-50K, a benchmark dataset comprising 50,000 image-mask pairs.

Related papers

• An End-to-End Automated Pipeline for Controllable Crack Data Synthesis [16.848359184857912]
  Vision-based crack inspection depends on segmentation networks whose reliability depends on the quantity, diversity and label quality of their training data.<n>This paper presents an end-to-end pipeline that produces labelled crack data without manual annotation and assesses the reliability of these data and of the detectors trained on them.
  arXiv  Detail & Related papers  (2026-09-11T04:40:01Z)
• SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation [0.8717253904965373]
  Source-free unsupervised domain adaptation (SFUDA) adapts a pretrained model to an unlabeled target domain without requiring access to sensitive source data.<n>We introduce a novel SFUDA framework built on Symmetrical Flow Matching.<n>We evaluate on abdominal multi-organ and cardiac segmentation, covering cross-modality MRI->CT shifts, and multi-site prostate segmentation.
  arXiv  Detail & Related papers  (2026-08-23T18:09:39Z)
• SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization [64.6372217552272]
  Public editing datasets contain millions of structurally identical (original, edited) pairs to IML training samples, lacking only pixel-level masks.<n>We propose SIGMA, which performs semantic-feature differencing in a vision foundation backbone.<n>It produces a 1.1M IML training set that improves six diverse detectors by +18.34% F1 across five datasets.
  arXiv  Detail & Related papers  (2026-05-27T03:55:13Z)
• FMS$^2$: Unified Flow Matching for Segmentation and Synthesis of Thin Structures [1.3111058225843968]
  We propose FMS$2$, a flow-matching framework with two modules.<n>SegFlow is a 2.96M- parameter segmentation model built on a standard encoder-decoder backbone.<n> SynFlow is a mask-conditioned mask $rightarrow$ image generator that produces pixel-aligned synthetic image-mask pairs.
  arXiv  Detail & Related papers  (2026-03-14T00:04:25Z)
• MaskOpt: A Large-Scale Mask Optimization Dataset to Advance AI in Integrated Circuit Manufacturing [9.945697214043385]
  We present MaskOpt, a large-scale benchmark dataset constructed from real IC designs at the 45$mathrmnm$ node.<n>We evaluate state-of-the-art deep learning models for IC mask optimization to build up benchmarks.
  arXiv  Detail & Related papers  (2025-12-18T05:53:45Z)
• Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation [57.37991748282666]
  We propose a paired, diffusion-guided paradigm that fuses the strengths of sample mixing and diffusion synthesis.<n>For each real image, a synthetic counterpart is generated under the same mask and the pair is used as a controllable input for Mask-Consistent Paired Mixing (MCPMix)<n>This produces a continuous family of intermediate samples that smoothly bridges synthetic and real appearances under shared geometry.
  arXiv  Detail & Related papers  (2025-11-05T06:14:19Z)
• FTCFormer: Fuzzy Token Clustering Transformer for Image Classification [22.410199372985584]
  Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks.<n>Most transformer architectures embed images into uniform, grid-based vision tokens, neglecting the underlying semantic meanings of image regions.<n>We propose Fuzzy Token Clustering Transformer (FTCFormer) to dynamically generate vision tokens based on the semantic meanings instead of spatial positions.
  arXiv  Detail & Related papers  (2025-07-14T13:49:47Z)
• High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution [87.56382172827526]
  High-frequency regions are most critical for reconstruction.<n>We propose a training-free adaptive masking module for acceleration.<n>Our method reduces FLOPs by 24--43% for state-of-the-art models.
  arXiv  Detail & Related papers  (2025-05-11T13:18:03Z)
• CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation [1.9393128408121891]
  Existing generative models fail to address the need for high-quality, simultaneous image-mask generation.<n>We propose CoSimGen, a diffusion-based framework for controllable simultaneous image and mask generation.<n>CoSimGen achieves state-of-the-art performance across all datasets, achieving the lowest KID of 0.11 and LPIPS of 0.53 across datasets.
  arXiv  Detail & Related papers  (2025-03-25T13:48:22Z)
• High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation [109.19165503929992]
  We present MaskCLIP++, which uses ground-truth masks instead of generated masks to enhance the mask classification capability of CLIP.<n>After low-cost fine-tuning, MaskCLIP++ significantly improves the mask classification performance on multi-domain datasets.<n>We achieve performance improvements of +1.7, +2.3, +2.1, +3.1, and +0.3 mIoU on the A-847, PC-459, A-150, PC-59, and PAS-20 datasets.
  arXiv  Detail & Related papers  (2024-12-16T05:44:45Z)
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• CrackSCF: Lightweight Cascaded Fusion Network for Robust and Efficient Structural Crack Segmentation [36.93774494071781]
  CrackSCF is a lightweight Cascaded Fusion Crack Network designed to achieve robust crack segmentation.<n>This approach efficiently captures local patterns while operating with a minimal computational footprint.<n>The experimental results show that the CrackSCF method consistently outperforms the existing methods.
  arXiv  Detail & Related papers  (2024-08-23T03:21:51Z)
• Mask Propagation for Efficient Video Semantic Segmentation [63.09523058489429]
  Video Semantic baseline degradation (VSS) involves assigning a semantic label to each pixel in a video sequence. We propose an efficient mask propagation framework for VSS, called SSSS. Our framework reduces up to 4x FLOPs compared to the per-frame Mask2Former with only up to 2% mIoU on the Cityscapes validation set.
  arXiv  Detail & Related papers  (2023-10-29T09:55:28Z)
• FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models [62.009002395326384]
  FreeMask resorts to synthetic images from generative models to ease the burden of data collection and annotation procedures. We first synthesize abundant training images conditioned on the semantic masks provided by realistic datasets. We investigate the role of synthetic images by joint training with real images, or pre-training for real images.
  arXiv  Detail & Related papers  (2023-10-23T17:57:27Z)
• CVFC: Attention-Based Cross-View Feature Consistency for Weakly Supervised Semantic Segmentation of Pathology Images [3.2128744424771725]
  Histopathology image segmentation is the gold standard for diagnosing cancer. Many studies now use imagelevel labels to achieve pixel-level segmentation to reduce the need for fine-grained annotation. We propose an attention-based cross-view feature consistency end-to-end pseudo-mask generation framework named CVFC.
  arXiv  Detail & Related papers  (2023-08-21T03:50:09Z)
• You Can Mask More For Extremely Low-Bitrate Image Compression [80.7692466922499]
  Learned image compression (LIC) methods have experienced significant progress during recent years. LIC methods fail to explicitly explore the image structure and texture components crucial for image compression. We present DA-Mask that samples visible patches based on the structure and texture of original images. We propose a simple yet effective masked compression model (MCM), the first framework that unifies LIC and LIC end-to-end for extremely low-bitrate compression.
  arXiv  Detail & Related papers  (2023-06-27T15:36:22Z)
• Recovering compressed images for automatic crack segmentation using generative models [13.519853801218005]
  We develop a recovery framework for automatic crack segmentation of compressed crack images based on this new CS method. Our recovery framework is illustrated by comparing with three existing CS algorithms.
  arXiv  Detail & Related papers  (2020-03-06T04:48:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.