EV-CGNet：共视聚焦的3D引导2D事件关键点检测网络
EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Network
事件相机关键点检测与描述子学习可复用于跨模态/跨视角匹配任务；其共视区域聚焦检测思路可迁移到任何需要抑制非重叠区域误检的匹配流程（如宽基线立体、多相机标定）。
原文依据 the limited use of co-visible information often results in excessive keypoint detection in non-matching regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件关键点检测因能通过匹配建立空间关联而备受关注，这是众多计算机视觉任务的基础。然而，由于难以在充分利用事件数据与兼容已有算法之间取得平衡，实现鲁棒的事件关键点检测仍具挑战性。此外，共视信息利用不足往往导致在非匹配区域检测出过多关键点，从而产生错误匹配。为解决这些挑战，我们提出一种新颖的共视聚焦3D引导2D事件关键点检测网络（EV-CGNet），其主要由3D引导2D特征原型学习（G2PL）模块与共视区域聚焦的检测器与描述子学习（CDDL）模块组成。所提方法具有若干优点。首先，G2PL模块能够利用事件点的细粒度时空线索来引导事件帧特征原型的学习。其次，CDDL模块能够将关键点检测聚焦于共视区域，从而确保匹配准确。在六个具有挑战性的基准上的全面实验评估表明，我们的方法显著优于最优的事件关键点检测方法。
英文原文摘要 1285 字符
Event keypoint detection has garnered significant attention due to its ability to establish spatial associations through matching, which is fundamental for various computer vision tasks. However, achieving robust event keypoint detection remains challenging due to the difficulty in balancing the exploitation of event data and compatibility with established algorithms. Moreover, the limited use of co-visible information often results in excessive keypoint detection in non-matching regions, leading to incorrect matches. To address these challenges, we propose a novel Co-visible Focused 3D-guided 2D Event Keypoint Detection Network (EV-CGNet), which mainly consists of a 3D-guided 2D feature prototype learning (G2PL) module and a co-visible region-focused detector and descriptor learning (CDDL) module. The proposed method enjoys several merits. First, the proposed G2PL module can leverage fine-grained spatio-temporal cues from event points to guide the learning of event frame feature prototypes. Second, the proposed CDDL module can focus keypoint detection on co-visible regions, ensuring accurate matches. Comprehensive experimental evaluations on six challenging benchmarks show that our method significantly outperforms state-of-the-art event keypoint detection methods.