Research map / Video / Video segmentation and tracking
Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying1, dt=4 | AEE: 2.02 -> 1.77 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying2, dt=4 | AEE: 2.85 -> 2.52 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying3, dt=4 | AEE: 2.49 -> 2.23 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC outdoor day1, dt=4 | AEE: 1.09 -> 0.99 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying1, dt=1 | AEE: 0.58 -> 0.57 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying2, dt=1 | AEE: 0.81 -> 0.79 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC indoor flying3, dt=1 | AEE: 0.73 -> 0.72 | Helped |
| Use STE-FlowNet instead of the strongest listed baseline | event-based optical flow estimation · MVSEC outdoor day1, dt=1 | AEE: 0.32 -> 0.42 | Hurt |
| Add ConvGRU temporal feature extraction and IRR (ablation) | STE-FlowNet · MVSEC indoor flying1, dt=4 | AEE: 4.77 -> 1.77 | Helped |
| Add multiple intermediate losses (ablation) | STE-FlowNet · MVSEC indoor flying1, dt=4 | AEE: 1.96 -> 1.77 | Helped |
| Add the correlation layer rather than directly sending flows (ablation) | STE-FlowNet · MVSEC indoor flying1, dt=4 | AEE: 2.11 -> 1.77 | Helped |
| Add IRR (ablation) | STE-FlowNet · MVSEC indoor flying1, dt=1 | AEE: 0.63 -> 0.59 | Helped |
Closest papers by meaning
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.89)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.88)
- EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation (CVPR 2025 · similarity 0.87)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing (ICML 2025 · similarity 0.87)
- State Space Models for Event Cameras (CVPR 2024 · 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.