{"title":"NCMNet:用于双视图对应性剪枝的邻居一致性挖掘网络。","authors":"Xin Liu;Rong Qin;Junchi Yan;Jufeng Yang","doi":"10.1109/TPAMI.2024.3462453","DOIUrl":null,"url":null,"abstract":"Correspondence pruning plays a crucial role in a variety of feature matching based tasks, which aims at identifying correct correspondences (inliers) from initial ones. Seeking consistent \n<inline-formula><tex-math>$k$</tex-math></inline-formula>\n-nearest neighbors in both coordinate and feature spaces is a prevalent strategy employed in previous approaches. However, the vicinity of an inlier contains numerous irregular false correspondences (outliers), which leads them to mistakenly become neighbors according to the similarity constraint of nearest neighbors. To tackle this issue, we propose a global-graph space to seek consistent neighbors with similar graph structures. This is achieved by using a global connected graph to explicitly render the affinity relationship between correspondences based on the spatial and feature consistency. Furthermore, to enhance the robustness of method for various matching scenes, we develop a neighbor consistency block to adequately leverage the potential of three types of neighbors. The consistency can be progressively mined by sequentially extracting intra-neighbor context and exploring inter-neighbor interactions. Ultimately, we present a Neighbor Consistency Mining Network (NCMNet) to estimate the parametric models and remove outliers. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on various benchmarks for two-view geometry estimation. Meanwhile, four extended tasks, including remote sensing image registration, point cloud registration, 3D reconstruction, and visual localization, are conducted to test the generalization ability.","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"NCMNet: Neighbor Consistency Mining Network for Two-View Correspondence Pruning\",\"authors\":\"Xin Liu;Rong Qin;Junchi Yan;Jufeng Yang\",\"doi\":\"10.1109/TPAMI.2024.3462453\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Correspondence pruning plays a crucial role in a variety of feature matching based tasks, which aims at identifying correct correspondences (inliers) from initial ones. Seeking consistent \\n<inline-formula><tex-math>$k$</tex-math></inline-formula>\\n-nearest neighbors in both coordinate and feature spaces is a prevalent strategy employed in previous approaches. However, the vicinity of an inlier contains numerous irregular false correspondences (outliers), which leads them to mistakenly become neighbors according to the similarity constraint of nearest neighbors. To tackle this issue, we propose a global-graph space to seek consistent neighbors with similar graph structures. This is achieved by using a global connected graph to explicitly render the affinity relationship between correspondences based on the spatial and feature consistency. Furthermore, to enhance the robustness of method for various matching scenes, we develop a neighbor consistency block to adequately leverage the potential of three types of neighbors. The consistency can be progressively mined by sequentially extracting intra-neighbor context and exploring inter-neighbor interactions. Ultimately, we present a Neighbor Consistency Mining Network (NCMNet) to estimate the parametric models and remove outliers. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on various benchmarks for two-view geometry estimation. Meanwhile, four extended tasks, including remote sensing image registration, point cloud registration, 3D reconstruction, and visual localization, are conducted to test the generalization ability.\",\"PeriodicalId\":94034,\"journal\":{\"name\":\"IEEE transactions on pattern analysis and machine intelligence\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-10-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on pattern analysis and machine intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10705098/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10705098/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
对应关系剪枝在各种基于特征匹配的任务中起着至关重要的作用,其目的是从初始对应关系中识别出正确的对应关系(离群值)。在坐标空间和特征空间中寻找一致的 k 近邻是以往方法中普遍采用的策略。然而,离群值附近包含大量不规则的虚假对应关系(离群值),这导致它们根据近邻的相似性约束错误地成为邻居。为了解决这个问题,我们提出了一个全局图空间,以寻求具有相似图结构的一致邻居。这是通过使用全局连接图来明确呈现基于空间和特征一致性的对应关系之间的亲缘关系来实现的。此外,为了增强该方法在各种匹配场景下的鲁棒性,我们开发了一个邻居一致性模块,以充分发挥三类邻居的潜力。通过依次提取邻居内部上下文和探索邻居之间的相互作用,可以逐步挖掘一致性。最后,我们提出了一个邻居一致性挖掘网络(NCMNet),用于估计参数模型和去除异常值。广泛的实验结果表明,在双视角几何估算的各种基准测试中,所提出的方法优于其他最先进的方法。同时,还进行了四项扩展任务,包括遥感图像配准、点云配准、三维重建和视觉定位,以测试其泛化能力。
NCMNet: Neighbor Consistency Mining Network for Two-View Correspondence Pruning
Correspondence pruning plays a crucial role in a variety of feature matching based tasks, which aims at identifying correct correspondences (inliers) from initial ones. Seeking consistent
$k$
-nearest neighbors in both coordinate and feature spaces is a prevalent strategy employed in previous approaches. However, the vicinity of an inlier contains numerous irregular false correspondences (outliers), which leads them to mistakenly become neighbors according to the similarity constraint of nearest neighbors. To tackle this issue, we propose a global-graph space to seek consistent neighbors with similar graph structures. This is achieved by using a global connected graph to explicitly render the affinity relationship between correspondences based on the spatial and feature consistency. Furthermore, to enhance the robustness of method for various matching scenes, we develop a neighbor consistency block to adequately leverage the potential of three types of neighbors. The consistency can be progressively mined by sequentially extracting intra-neighbor context and exploring inter-neighbor interactions. Ultimately, we present a Neighbor Consistency Mining Network (NCMNet) to estimate the parametric models and remove outliers. Extensive experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on various benchmarks for two-view geometry estimation. Meanwhile, four extended tasks, including remote sensing image registration, point cloud registration, 3D reconstruction, and visual localization, are conducted to test the generalization ability.