Research map / Video / Video segmentation and tracking
Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation
Xueyan Huang, Yueyi Zhang, Zhiwei Xiong
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 |
|---|---|---|---|
| use progressive event-to-map alignment with the proposed time-surface loss | event-based rotational motion estimation · Event-Camera dataset | RMSw: poster rotation: 11.67 -> 9.98; dynamic rotation: 6.40 -> 4.78; shapes rotation: 48.90 -> 10.62; classroom: 5.19 -> 2.61 | Improved |
| use progressive event-to-map alignment with the proposed time-surface loss | event-based homography motion estimation · poster sequences: translation, 6dof, hdr | RMSw: translation: 17.14 -> 13.28; 6dof: 51.47 -> 22.54; hdr: 22.08 -> 17.08 | Improved |
| use progressive event-to-map alignment with the proposed time-surface loss | event-based 6-DOF motion estimation · MVSEC indoor flying1 and outdoor driving1 | RMSw: indoor flying1: 1.38 -> 1.05; outdoor driving1: 4.00 -> 2.72 | Improved |
| increase sampled events from 0.1k to 1k to 10k to 30k (ablation) | progressive alignment · poster rotation | RMSw: 10.23 -> 10.11 -> 9.99 -> 9.98 | Improved |
| increase sampled events from 0.1k to 1k to 10k to 30k (ablation) | progressive alignment · shapes rotation | RMSw: 10.92 -> 10.85 -> 10.55 -> 10.62 | Mixed |
| add bidirectional warping instead of using unidirectional warping (ablation) | Ours-30k with dynamic batches · poster rotation | RMSw: 11.05 -> 9.98 | Improved |
| add bidirectional warping instead of using unidirectional warping (ablation) | Ours-30k with dynamic batches · shapes rotation | RMSw: 15.08 -> 10.62 | Improved |
| use dynamic rather than fixed-size batches (ablation) | Ours-30k with bidirectional warping · poster rotation | RMSw: 10.21 -> 9.98 | Improved |
| use dynamic rather than fixed-size batches (ablation) | Ours-30k with bidirectional warping · shapes rotation | RMSw: 18.39 -> 10.62 | Improved |
| use bidirectional warping and dynamic batches rather than unidirectional warping and fixed-size batches (ablation) | Ours-30k · poster rotation | RMSw: 11.10 -> 9.98 | Improved |
| use bidirectional warping and dynamic batches rather than unidirectional warping and fixed-size batches (ablation) | Ours-30k · shapes rotation | RMSw: 22.41 -> 10.62 | Improved |
| use bidirectional rather than unidirectional warping (ablation) | Ours-30k with dynamic batches · poster rotation | Time: 15.9 -> 35.7 | Hurt |
Closest papers by meaning
- The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data (ICCV 2021 · similarity 0.90)
- Event-based Optical Flow Using Spatio-temporal Registration (TPAMI 2026 · similarity 0.89)
- A 5-Point Minimal Solver for Event Camera Relative Motion Estimation (ICCV 2023 · similarity 0.88)
- EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction (AAAI 2025 · similarity 0.87)
- Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow (CVPR 2025 · similarity 0.85)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.85)
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.
