Research map / Detection and segmentation / 3D detection and driving
EV-CGNet: Co-visible Focused 3D-guided 2D Event Keypoint Detection Network
Yuan Gao, Tianle Ding, Yuqing Zhu, Tianzhu Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add G2PL module (3D-guided 2D prototypes) to the frame-only baseline (ablation) | EV-CGNet · HVGA ATIS Corner, 25ms | reprojection error (px): 5.36 -> 0.51 | Improved |
| add CDDL module (co-visible region focus) to the frame-only baseline (ablation) | EV-CGNet · HVGA ATIS Corner, 25ms | reprojection error (px): 5.36 -> 0.39 | Improved |
| add G2PL on top of CDDL (ablation) | EV-CGNet · HVGA ATIS Corner, 100ms | reprojection error (px): 0.59 -> 0.42 | Improved |
| add CDDL on top of G2PL (ablation) | EV-CGNet · HVGA ATIS Corner, 100ms | reprojection error (px): 0.73 -> 0.42 | Improved |
| increase number of event point prototypes from 2 to 16 (ablation) | G2PL · HVGA ATIS Corner, 25ms | reprojection error (px): 0.46 -> 0.27 | Improved |
| increase number of event point prototypes from 16 to 32 (ablation) | G2PL · HVGA ATIS Corner, 25ms | reprojection error (px): 0.27 -> 0.29 | No clear effect |
| replace EV-CGNet detector with prior SuperEvent on SLAM | OKVIS2 SLAM · VECtor corr-dolly | ATE (cm): 33.13 -> 10.03 | Improved |
| use EV-CGNet instead of SuperEvent for long-distance loop closure | OKVIS2 SLAM · TUM-VIE loop-floor 0 | ATE (cm): 4.96 -> 1.35 | Improved |
Closest papers by meaning
- SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras (CVPR 2024 · similarity 0.87)
- SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM (ICCV 2025 · similarity 0.85)
- KeypointDETR: An End-to-End 3D Keypoint Detector (ECCV 2024 · similarity 0.84)
- Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features (CVPR 2024 · similarity 0.84)
- ED-Pose++: Enhanced Explicit Box Detection for Conventional and Interactive Multi-Object Keypoint Detection (TPAMI 2025 · similarity 0.84)
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
