EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Network
Yuan Gao, Tianle Ding, Yuqing Zhu, Tianzhu Zhang
Abstract
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 3Dguided 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 finegrained 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 covisible regions, ensuring accurate matches. Comprehensive experimental evaluations on six challenging benchmarks show that our method significantly outperforms state-ofthe-art event keypoint detection methods.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- SuperEvent: Cross-Modal Learning of Event-Based Keypoint Detection for SLAM cites Event-aided Direct Sparse Odometry
- SuperEvent: Cross-Modal Learning of Event-Based Keypoint Detection for SLAM cites SD2Event: Self-Supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras
Builds on6
- Event-aided Direct Sparse OdometryJavier Hidalgo-Carrió, Guillermo Gallego, Davide ScaramuzzaCVPR 2022 · 107 citations
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian SplattingHaiqian Han, Jianing Li, Henglu Wei, Xiangyang JiNeurIPS 2024 · 39 citations
- EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and EventsZehao Chen, Zhanfeng Liao, De Ma, Huajin Tang et al.AAAI 2025 · 9 citations
- SuperEvent: Cross-Modal Learning of Event-Based Keypoint Detection for SLAMYannick Burkhardt, Simon Schaefer, Stefan LeuteneggerICCV 2025 · 7 citations
- SD2Event: Self-Supervised Learning of Dynamic Detectors and Contextual Descriptors for Event CamerasYuan Gao, Yuqing Zhu, Xinjun Li, Yimin Du et al.CVPR 2024
Related papers
- E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation LearningXiuhong Lin, Changjie Qiu, Zhipeng Cai, Siqi Shen et al.NeurIPS 2023 · 18 citations
- Learning Graph-embedded Key-event Back-tracing for Object Tracking in Event CloudsZhiyu Zhu, Junhui Hou, Xianqiang LyuNeurIPS 2022 · 48 citations
- Neural Outlier Rejection for Self-Supervised Keypoint LearningJiexiong Tang, Hanme Kim, Vitor Guizilini, Sudeep Pillai et al.ICLR 2020 · 40 citations
- Divide and Conquer: Question-Guided Spatio-Temporal Contextual Attention for Video Question AnsweringJianwen Jiang, Ziqiang Chen, Haojie Lin, Xibin Zhao et al.AAAI 2020 · 129 citations
- Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary DetectionJiaqi Tang, Zhaoyang Liu, Chen Qian, Wayne Wu et al.CVPR 2022 · 15 citations
