Research map / Detection and segmentation / CNN features
Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the Speed Invariant Time Surface instead of the standard Time Surface (ablation) | Random Forest event corner detector · HVGA ATIS Corner Dataset, Δt = 25ms | reprojection error: 5.79 -> 2.45 | Helped |
| Use the Speed Invariant Time Surface instead of the standard Time Surface (ablation) | Random Forest event corner detector · HVGA ATIS Corner Dataset, Δt = 50ms | reprojection error: 8.48 -> 3.03 | Helped |
| Use the Speed Invariant Time Surface instead of the standard Time Surface (ablation) | Random Forest event corner detector · HVGA ATIS Corner Dataset, Δt = 100ms | reprojection error: 12.26 -> 3.70 | Helped |
| Train SILC on DAVIS data rather than transfer the ATIS-trained model | SILC · Event-Camera dataset | 3D reprojection error (pix): 2.53 -> 2.16 | Helped |
| Train SILC on DAVIS data rather than transfer the ATIS-trained model | SILC · Event-Camera dataset | valid tracks (%): 47.3 -> 65.3 | Helped |
| Use the DAVIS-trained SILC detector instead of evHarris | Event corner detection and nearest-neighbor tracking · Event-Camera dataset | 3D reprojection error (pix): 2.46 -> 2.16 | Helped |
| Use the DAVIS-trained SILC detector instead of evFast | Event corner detection and nearest-neighbor tracking · Event-Camera dataset | valid tracks (%): 50.1 -> 65.3 | Helped |
| Use SILC instead of evFast | Event corner detection and nearest-neighbor tracking · HVGA ATIS Corner Dataset | feature-track lifetime | Mixed |
| Use SILC instead of evHarris or Arc | Event corner detection and nearest-neighbor tracking · HVGA ATIS Corner Dataset | track reliability | Helped |
Closest papers by meaning
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.85)
- SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras (CVPR 2024 · similarity 0.85)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 2024 · similarity 0.85)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · similarity 0.85)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.84)
- EventPillars: Pillar-based Efficient Representations for Event Data (AAAI 2025 · similarity 0.84)
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.