Defocus Blur detection via transformer encoder and edge guidance

doi:10.1007/s10489-022-03303-y

CIOMP OpenIR

	Defocus Blur detection via transformer encoder and edge guidance
	Z. J. Zhao; H. Yang and H. Y. Luo
	2022
发表期刊	Applied Intelligence
ISSN	0924-669X
卷号	52 期号:12 页码:14426-14439
摘要	Defocus blur detection (DBD) aims to separate blurred and unblurred regions for a given image. Benefiting from the powerful extraction capabilities of convolutional neural networks (CNNs), deep learning based defocus blur detection has achieved a remarkable progress compared with traditional methods. However, due to the limited local receptive field of CNNs, it is difficult to achieve satisfactory results in the detection of the low-contrast focal regions. Besides, the output maps of the most of previous works have coarse object boundaries and background clutter. In this paper, we propose a hybrid CNN-Transformer architecture with an edge guidance aggregation module (EGAM) and a feature fusion module (FFM) for DBD. In our knowledge, this is the first study to utilize a transformer encoder for DBD to capture the global context information. Additionally, an edge extraction network (EENet) is adopted to obtain local edge information of in-focus objects. To effectively aggregate local edge information and global semantic features, three EGAMs are integrated into an edge guidance fusion network (EGFNet). Benefiting from the rich edge information, the fused features can generate more accurate boundaries. Finally, three FFMs are cascaded as a hierarchical feature aggregation network (HFANet) to hierarchically decode and refine the feature maps. Experimental results on three widely used DBD datasets demonstrate that the proposed model outperforms the state-of-the-art approaches.
DOI	10.1007/s10489-022-03303-y
URL	查看原文
收录类别	sci ; ei
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/66512
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Z. J. Zhao,H. Yang and H. Y. Luo. Defocus Blur detection via transformer encoder and edge guidance[J]. Applied Intelligence,2022,52(12):14426-14439.
APA	Z. J. Zhao,&H. Yang and H. Y. Luo.(2022).Defocus Blur detection via transformer encoder and edge guidance.Applied Intelligence,52(12),14426-14439.
MLA	Z. J. Zhao,et al."Defocus Blur detection via transformer encoder and edge guidance".Applied Intelligence 52.12(2022):14426-14439.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Defocus Blur detecti（7944KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载