CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Xianglong, Jiang, Yunhan, Jiang, Xiaoheng, Xu, Mingling, Liu, Yang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917899569987584
author Shi, Xianglong
Jiang, Yunhan
Jiang, Xiaoheng
Xu, Mingling
Liu, Yang
author_facet Shi, Xianglong
Jiang, Yunhan
Jiang, Xiaoheng
Xu, Mingling
Liu, Yang
contents Crack Segmentation in industrial concrete surfaces is a challenging task because cracks usually exhibit intricate morphology with slender appearances. Traditional segmentation methods often struggle to accurately locate such cracks, leading to inefficiencies in maintenance and repair processes. In this paper, we propose a novel diffusion-based model with a cross-conditional encoder-decoder, named CrossDiff, which is the first to introduce the diffusion probabilistic model for the crack segmentation task. Specifically, CrossDiff integrates a cross-encoder and a cross-decoder into the diffusion model to constitute a cross-shaped diffusion model structure. The cross-encoder enhances the ability to retain crack details and the cross-decoder helps extract the semantic features of cracks. As a result, CrossDiff can better handle slender cracks. Extensive experiments were conducted on five challenging crack datasets including CFD, CrackTree200, DeepCrack, GAPs384, and Rissbilder. The results demonstrate that the proposed CrossDiff model achieves impressive performance, outperforming other state-of-the-art methods by 8.0% in terms of both Dice score and IoU. The code will be open-source soon.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation
Shi, Xianglong
Jiang, Yunhan
Jiang, Xiaoheng
Xu, Mingling
Liu, Yang
Computer Vision and Pattern Recognition
Crack Segmentation in industrial concrete surfaces is a challenging task because cracks usually exhibit intricate morphology with slender appearances. Traditional segmentation methods often struggle to accurately locate such cracks, leading to inefficiencies in maintenance and repair processes. In this paper, we propose a novel diffusion-based model with a cross-conditional encoder-decoder, named CrossDiff, which is the first to introduce the diffusion probabilistic model for the crack segmentation task. Specifically, CrossDiff integrates a cross-encoder and a cross-decoder into the diffusion model to constitute a cross-shaped diffusion model structure. The cross-encoder enhances the ability to retain crack details and the cross-decoder helps extract the semantic features of cracks. As a result, CrossDiff can better handle slender cracks. Extensive experiments were conducted on five challenging crack datasets including CFD, CrackTree200, DeepCrack, GAPs384, and Rissbilder. The results demonstrate that the proposed CrossDiff model achieves impressive performance, outperforming other state-of-the-art methods by 8.0% in terms of both Dice score and IoU. The code will be open-source soon.
title CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.12860