Research map / Video / Video segmentation and tracking
Realtime Time Synchronized Event-based Stereo
Alex Zihao Zhu, Yibo Chen, Kostas Daniilidis
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 time synchronization of events (IoU cost) (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 2.21 -> 0.89 | Improved |
| add time synchronization to IoU cost (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.43 -> 0.89 | Improved |
| add time synchronization to time cost (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.85 -> 1.30 | Improved |
| add union term (IoU instead of intersection only), with time sync (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.71 -> 0.89 | Improved |
| use IoU cost instead of timestamp cost, with time sync (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.30 -> 0.89 | Improved |
| use IoU cost instead of timestamp cost, without time sync (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.85 -> 1.43 | Improved |
| add outlier rejection (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 1.87 -> 0.89 | Improved |
| add outlier rejection (ablation) | TSES · MVSEC indoor_flying1 | mean depth error (m): 1.28 -> 0.36 | Improved |
| add velocity noise up to 20% of velocity norm (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 0.89 -> 0.96 | No clear effect |
| add 100% velocity noise (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 0.89 -> 1.97 | Hurt |
| increase window size from 8 to 24 pixels (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 2.40 -> 0.89 | Improved |
| increase window size from 24 to 32 pixels (ablation) | TSES · MVSEC indoor_flying1 | mean disparity error (pix): 0.89 -> 0.86 | No clear effect |
Closest papers by meaning
- Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds (ICCV 2021 · similarity 0.91)
- Edge-Guided Fusion and Motion Augmentation for Event-Image Stereo (ECCV 2024 · similarity 0.90)
- Event-Based Stereo Depth Estimation: A Survey (TPAMI 2025 · similarity 0.90)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.87)
- EventPS: Real-Time Photometric Stereo Using an Event Camera (CVPR 2024 · similarity 0.87)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.86)
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.
