Research map / Video / Video segmentation and tracking
TMA: Temporal Motion Aggregation for Event-based Optical Flow
Haotian Liu, Guang Chen, Sanqing Qu, Yanping Zhang, Zhijun Li, Alois Knoll, Changjun Jiang
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 temporal motion aggregation (TMA) in place of E-RAFT | RAFT-style event flow · DSEC-Flow test | EPE: 0.79 -> 0.74 | Improved |
| TMA needs fewer refinement iterations, reducing inference time versus E-RAFT | TMA · DSEC-Flow test | inference time (ms): 52 -> 30 | Improved |
| increase event splits from 1 to 5 (ablation) | TMA · DSEC-Flow test | EPE: 0.79 -> 0.74 | Improved |
| increase event splits from 5 to 7 (ablation) | TMA · DSEC-Flow test | EPE / time: EPE 0.74 -> 0.74, time 30 -> 50 ms | No clear effect |
| add linear lookup versus no lookup (ablation) | TMA · DSEC-Flow test | EPE: 0.78 -> 0.74 | Improved |
| linear lookup instead of same sampling coordinates (ablation) | TMA · DSEC-Flow test | EPE: 0.76 -> 0.74 | Improved |
| add motion pattern aggregation layer (1 layer vs 0) (ablation) | TMA · DSEC-Flow test | 1PE: 11.36 -> 10.86 | Improved |
| pair intermediate features with last feature instead of circular pairing (ablation) | Pattern aggregation module · DSEC-Flow test | EPE: 0.76 -> 0.74 | Improved |
| stack 2 aggregation layers instead of 1 (ablation) | TMA · DSEC-Flow test | EPE: 0.74 -> 0.75 | Hurt |
| increase refinement iterations from 2 to 6 (ablation) | TMA · DSEC-Flow test | EPE: 0.83 -> 0.74 | Improved |
| increase lookup search radius (ablation) | TMA · DSEC-Flow test | EPE: 0.74 (radius 3) vs 0.75 (radius 4) | No clear effect |
| add TMA versus E-RAFT on MVSEC outdoor_day1 dt=4 | TMA · MVSEC outdoor_day1 (dt=4) | EPE: 0.72 -> 0.70 | Improved |
Closest papers by meaning
- BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation (AAAI 2026 · similarity 0.92)
- Event-based Optical Flow Using Spatio-temporal Registration (TPAMI 2026 · similarity 0.91)
- EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation (CVPR 2025 · similarity 0.91)
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.89)
- Efficient Meshflow and Optical Flow Estimation from Event Cameras (CVPR 2024 · similarity 0.88)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.88)
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.
