Research map / 3D vision / Depth and stereo
Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks
Chankyu Lee, Adarsh Kumar Kosta, Alex Zihao Zhu, Kenneth Chaney, Kostas Daniilidis, Kaushik Roy
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 |
|---|---|---|---|
| convert the first residual block from ANN to SNN (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=1) | AEE: 1.28 -> 1.55 | Hurt |
| convert both residual blocks from ANN to SNN (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=1) | AEE: 1.28 -> 1.56 | Hurt |
| convert the first residual block from ANN to SNN (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 4.46 | Hurt |
| convert both residual blocks from ANN to SNN (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 4.61 | Hurt |
| increase number of event groups N from 2 to 4 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=1) | AEE: 1.28 -> 1.76 | Hurt |
| increase number of event groups N from 2 to 3 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 4.05 | Hurt |
| increase number of event groups N from 2 to 4 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 3.81 | No clear effect |
| raise smoothness weight lambda from 1 to 10 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=1) | AEE: 1.38 -> 1.28 | Improved |
| raise smoothness weight lambda from 1 to 10 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 4.22 | Hurt |
| raise smoothness weight lambda from 1 to 100 (ablation) | Spike-FlowNet · MVSEC indoor2 (dt=4) | AEE: 3.83 -> 4.01 | Hurt |
| use hybrid SNN-encoder plus ANN architecture instead of fully ANN (EV-FlowNet) | Spike-FlowNet · MVSEC indoor2 (dt=1) | AEE: 1.72 -> 1.28 | Improved |
| use SNN encoder instead of ANN encoder | Spike-FlowNet · MVSEC (mean of 4 sequences, dt=1) | encoder compute energy: 214.2x | Improved |
Later papers that compared with this method
1 later accepted paper reports Spike-FlowNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Optical Flow Estimation for Spiking Camera (CVPR 2022 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.89)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.89)
- Graph Neural Network Combining Event Stream and Periodic Aggregation for Low-Latency Event-based Vision (CVPR 2025 · similarity 0.88)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.88)
- SFOD: Spiking Fusion Object Detector (CVPR 2024 · similarity 0.87)
- Hybrid Spiking Vision Transformer for Object Detection with Event Cameras (ICML 2025 · 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.
