文献类型：期刊文献

英文题名：DAN: Distortion-aware Network for fisheye image rectification using graph reasoning

作者：Yan, Yongjia[1];Liu, Hongzhe[1,2];Zhang, Cheng[1];Xu, Cheng[1,2];Xu, Bingxin[1,2];Pan, Weiguo[1,2];Dai, Songyin[1,2];Song, Yiqing[1]

第一作者：Yan, Yongjia

通讯作者：Liu, HZ[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China

第一机构：北京联合大学北京市信息服务工程重点实验室

通讯机构：[1]corresponding author), Beijing Union Univ, 97 North Fourth Ring East Rd, Beijing 100101, Peoples R China.|[11417]北京联合大学;

年份：2025

卷号：156

外文期刊名：IMAGE AND VISION COMPUTING

收录：;EI(收录号：20251118024307);Scopus(收录号：2-s2.0-86000307427);WOS:【SCI-EXPANDED(收录号:WOS:001443680000001)】；

基金：This work was supported, the National Natural Science Foundation of China (Grant No. 62171042, 62102033, U24A20331) , the R&D Program of Beijing Municipal Education Commission (Grant No. KZ202211417048) , The Project of Construction and Support for high-level Innovative Teams of Beijing Municipal Institutions (Grant No. BPHR20220121) , Beijing Natural Science Foundation (Grant No. 4232026, 4242020) , the Academic Research Projects of Beijing Union University, China (No. ZKZD202302, ZK20202403) .

语种：英文

外文关键词：Fisheye image; Distortion rectification; Distortion pattern understanding; Graph reasoning

摘要：Despite the wide-field view of fisheye images, their application is still hindered by the presentation of distortions. Existing learning-based methods still suffer from artifacts and loss of details, especially at the image edges. To address this, we introduce the Distortion-aware Network (DAN), a novel deep network architecture for fisheye image rectification that leverages graph reasoning. Specifically, we employ the superior relational understanding capability of graph technology to associate distortion patterns in different regions, generating an accurate and globally consistent unwarping flow. Meanwhile, during the image reconstruction process, we utilize deformable convolution to construct same-resolution feature blocks and employ skip connections to supplement the detailed information. Additionally, we introduce a weight decay-based multi-scale loss function, enabling the model to focus more on accuracy at high-resolution layers while enhancing the model's generalization ability. To address the lack of quantitative evaluation standards for real fisheye images, we propose a new metric called the "Line Preservation Metric." Through qualitative and quantitative experiments on PLACE365, COCO2017 and real fisheye images, the proposed method proves to outperform existing methods in terms of performance and generalization.