Research map / Video / Video segmentation and tracking
Learning Optical Flow from Continuous Spike Streams
Rui Zhao, Ruiqin Xiong, Jing Zhao, Zhaofei Yu, Xiaopeng Fan, Tiejun Huang
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 |
|---|---|---|---|
| remove DSFT transform (ablation) | Spike2Flow · RSSF dt=20 | AEPE: 0.117 -> 0.236 | Hurt |
| remove SIA and JCD modules (ablation) | Spike2Flow · RSSF dt=60 | PO%: 6.98 -> 8.40 | Hurt |
| remove JCD module (ablation) | Spike2Flow · RSSF dt=60 | AEPE: 0.286 -> 0.310 | Hurt |
| remove SIA module (ablation) | Spike2Flow · RSSF dt=20 | AEPE: 0.117 -> 0.116 | No clear effect |
| remove SIA module (ablation) | Spike2Flow · RSSF dt=60 | PO%: 6.98 -> 7.24 | Hurt |
| add SIA module (compare C and B) (ablation) | Spike2Flow · RSSF dt=60 | PO%: 8.40 -> 7.88 | Improved |
| number of input spike frames 1 -> 21 (ablation) | Spike2Flow · RSSF dt=20 | AEPE: 0.174 -> 0.117 | Improved |
| number of input spike frames 1 -> 21 (ablation) | Spike2Flow · RSSF dt=60 | PO%: 15.01 -> 6.98 | Improved |
| number of input spike frames 15 -> 21 (ablation) | Spike2Flow · RSSF dt=20 | PO%: 3.01 -> 2.57 | Improved |
| spike stream input instead of averaged image | RAFT · RSSF dt=20 | AEPE: 0.244 -> 0.181 | Improved |
| spike stream input instead of averaged image | GMA · RSSF dt=20 | AEPE: 0.226 -> 0.230 | No clear effect |
| spike stream input instead of averaged image | SCV · RSSF dt=20 | AEPE: 0.534 -> 0.570 | Hurt |
Closest papers by meaning
- Optical Flow for Spike Camera with Hierarchical Spatial-Temporal Spike Fusion (AAAI 2024 · similarity 0.91)
- Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera (AAAI 2024 · similarity 0.88)
- Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations (CVPR 2024 · similarity 0.88)
- Finding Visual Saliency in Continuous Spike Stream (AAAI 2024 · similarity 0.88)
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.88)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 2024 · 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.
