Research map / Detection and segmentation / CNN features
luvHarris: A Practical Corner Detector for Event-Cameras
Arren Glover, Dinale A., de Souza Rosa L., Bamford S., Chiara Bartolozzi
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 |
|---|---|---|---|
| decouple Harris computation from events using a look-up table (luvHarris) instead of ARC | corner detector · Event throughput | M events/s: 3.27 -> 8.59 | Improved |
| use luvHarris instead of eHarris | corner detector · Event throughput | M events/s: 0.16 -> 8.59 | Improved |
| use luvHarris instead of eHarris | corner detector · RPG 6-DoF datasets, precision at 50% recall | precision: up to 40% | Improved |
| add event filter (ablation) | ARC · shapes_6dof | accuracy | Improved |
| add event filter (ablation) | Harris-based algorithms (eHarris, luvHarris) · RPG 6-DoF datasets | accuracy | Improved |
| add event filter (ablation) | SITS surface · RPG 6-DoF datasets | accuracy | No clear effect |
| add event filter (ablation) | TOS surface · RPG 6-DoF datasets | accuracy | Improved |
| use luvHarris instead of eHarris with the same surface type (SITS or TOS) | corner detector · RPG 6-DoF datasets | accuracy | Improved |
| increase k_TOS (ablation) | luvHarris · Event throughput | M events/s | Hurt |
| use FAST instead of ARC or eHarris | corner detector · RPG 6-DoF datasets | accuracy | Hurt |
Closest papers by meaning
- Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras (CVPR 2019 · similarity 0.89)
- High-Throughput Event-Based Feature Detection and Tracking on an Embedded CPU (ECCV 2026 · similarity 0.86)
- From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras (CVPR 2026 · similarity 0.86)
- Event-Based Stereo Depth Estimation: A Survey (TPAMI 2025 · similarity 0.85)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.83)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 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.
