Research map / Detection and segmentation / CNN features
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection
Jae-Young Kang, Hoonhee Cho, Kuk-Jin Yoon
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 semantic voxel source (G+S) (ablation) | geometric plane-sweep baseline · DSEC-3DOD easy | mAP 3D: 12.92 -> 14.60 | Improved |
| add dual semantic-geometric filter (SDR+GSV) (ablation) | G+S · DSEC-3DOD easy | mAP 3D: 14.60 -> 19.12 | Improved |
| add SDR alone (ablation) | G+S · DSEC-3DOD easy | mAP 3D: 14.60 -> 15.85 | Improved |
| add GSV alone (ablation) | G+S · DSEC-3DOD easy | mAP 3D: 14.60 -> 17.08 | Improved |
| add object-centric ROI alignment (ablation) | DSGF · DSEC-3DOD easy | mAP 3D: 19.12 -> 21.66 | Improved |
| add OCRA (ablation) | G+S · DSEC-3DOD easy | mAP 3D: 14.60 -> 15.95 | Improved |
| add OCRA (ablation) | G · DSEC-3DOD easy | mAP 3D: 12.92 -> 14.56 | Improved |
| add SDR (ablation) | depth refinement · depth outlier (>0.2m) | outlier ratio: 0.715 -> 0.696 | Improved |
| add RGB fusion at motion x1 (ablation) | Ours · DSEC-3DOD | VEH AP3D: 23.47 -> 25.23 | Improved |
| add RGB fusion at motion x2 (ablation) | Ours · DSEC-3DOD | PED AP3D: 19.04 -> 10.50 | Hurt |
| event-only stereo instead of Ev-3DOD at motion x4 (ablation) | Ev-3DOD · DSEC-3DOD VEH | AP3D easy: 6.36 -> 22.72 | Improved |
| event-only stereo vs LiDAR+RGB+Event at motion x1 | Ev-3DOD · DSEC-3DOD VEH | AP3D easy: 29.53 -> 23.47 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DSGN — DSGN: Deep Stereo Geometry Network for 3D Object Detection (CVPR 2020) · better on 5 of 5 shared results
- Ev-3DOD — Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras (CVPR 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras (CVPR 2025 · similarity 0.91)
- Temporal Event Stereo via Joint Learning with Stereoscopic Flow (ECCV 2024 · similarity 0.91)
- Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow (TPAMI 2025 · similarity 0.90)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.88)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.88)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.87)
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.
